%% This BibTeX bibliography file was created using BibDesk. %% http://bibdesk.sourceforge.net/ %% Created for Tim Furche at 2006-03-09 12:43:57 +0100 %% Saved with string encoding Western (ASCII) @STRING{bncod = " Proc. British National Conf. on Databases"} @STRING{edbt = " Proc. Extending Database Technology"} @STRING{icde = " Proc. Intl. Conf. on Data Engineering"} @STRING{icdt = " Proc. Intl. Conf. on Database Theory"} @STRING{iclp = " Proc. Intl. Conf. on Logic Programming"} @STRING{iswc = " Proc. Intl. Semantic Web Conf."} @STRING{lpar = " Proc. Intl. Conf. on Logic for Programming, Artificial Intelligence and Reasoning"} @STRING{odbase = " Proc. Intl. Conf. on Ontologies, Databases, and Applications of Semantics for Large Scale Information Systems"} @STRING{pods = " Proc. ACM Symposium on Principles of Database Systems"} @STRING{ppswr = " Proc. Workshop on Principles and Practice of Semantic Web Reasoning"} @STRING{sac = " Proc. Symposium of Applied Computing"} @STRING{sigmod = " Proc. ACM SIGMOD Conf."} @STRING{vldb = " Proc. Intl. Conf. on Very Large Databases"} @STRING{www = " Proc. Intl. World Wide Web Conf."} @inproceedings{Lu_TwigDewey_VLDB_2005, Author = {Lu, Jiaheng and Ling, Tok Wang and Chan, Chee-Yong and Chen, Ting}, Booktitle = {Proc. Int'l. Conf. on Very Large Data Bases}, Date-Added = {2006-03-09 12:42:22 +0100}, Date-Modified = {2006-03-09 12:43:55 +0100}, Isbn = {1-59593-154-6}, Keywords = {XML query optimization evaluation twig holistic joins dewey tree encoding}, Location = {Trondheim, Norway}, Pages = {193--204}, Publisher = {VLDB Endowment}, Title = {{From Region Encoding to Extended Dewey: On Efficient Processing of XML Twig Pattern Matching}}, Year = {2005}, Abstract = {Finding all the occurrences of a twig pattern in an XML database is a core operation for efficient evaluation of XML queries. A number of algorithms have been proposed to process a twig query based on region encoding labeling scheme. While region encoding supports efficient determination of structural relationship between two elements, we observe that the information within a single label is very limited. In this paper, we propose a new labeling scheme, called extended Dewey. This is a powerful labeling scheme, since from the label of an element alone, we can derive all the elements names along the path from the root to the element. Based on extended Dewey, we design a novel holistic twig join algorithm, called TJFast. Unlike all previous algorithms based on region encoding, to answer a twig query, TJFast only needs to access the labels of the leaf query nodes. Through this, not only do we reduce disk access, but we also support the efficient evaluation of queries with wildcards in branching nodes, which is very difficult to be answered by algorithms based on region encoding. Finally, we report our experimental results to show that our algorithms are superior to previous approaches in terms of the number of elements scanned, the size of intermediate results and query performance.}} @article{Bry_XChange_JWE_2006, Author = {Bry, Fran{\c c}ois and Eckert, Michael and P{\u a}tr{\^a}njan, Paula-Lavinia}, Date-Added = {2006-03-06 17:37:10 +0100}, Date-Modified = {2006-03-06 17:38:10 +0100}, Journal = {Journal of Web Engineering}, Number = {1}, Pages = {3--24}, Title = {{Reactivity on the Web: Paradigms and Applications of the Language XChange}}, Url = {http://www.pms.ifi.lmu.de/publikationen#PMS-FB-2006-3}, Volume = {5}, Year = {2006}, Abstract = {Reactivity on the Web is an emerging research issue covering: updating data on the Web, exchanging information about events (such as executed updates) between Web sites, and reacting to combinations of such events. Reactivity plays an important role for upcoming Web systems such as online marketplaces, adaptive Web and Semantic Web systems, as well as Web services and Grids. This article introduces the paradigms upon which the high-level language XChange for programming reactive behaviour and distributed applications on the Web relies. Then, it briefly presents the main syntactical constructs of XChange and their declarative and operational semantics.}} @inproceedings{Bry_TenTheses_RLI_2005, Author = {Bry, Fran{\c c}ois and Marchiori, Massimo}, Booktitle = {Proc. of W3C Workshop on Rule Languages for Interoperability}, Date-Added = {2006-03-06 17:33:00 +0100}, Date-Modified = {2006-03-06 17:35:22 +0100}, Organization = {W3C}, Title = {{Ten Theses on Logic Languages for the Semantic Web}}, Url = {http://www.pms.ifi.lmu.de/publikationen#PMS-FB-2005-7}, Year = {2005}, Abstract = {This articles discusses the logic, or logic-based, languages required for a full deployment of the Semantic Web. It presents ten theses addressing (1) the kinds of logic languages needed, (2) data and data processing, (3) semantics, and (4) engineering and rendering issues.}} @mastersthesis{Linse_XQuery2Xcerpt_DA_2006, Author = {Linse, Benedikt}, Date-Added = {2006-03-06 10:26:17 +0100}, Date-Modified = {2006-03-06 10:28:43 +0100}, Keywords = {XML XQuery Xcerpt translation nested construction}, School = {Institute for Informatics, University of Munich}, Title = {{Automatic Translation between XQuery and Xcerpt}}, Type = {{Diplomarbeit/Master thesis}}, Url = {http://www.pms.ifi.lmu.de/publikationen#DA_Benedikt.Linse}, Year = {2006}} @inproceedings{Regin_AllDifferent_AAAI_1994, Author = {R{\'e}gin, Jean-Charles}, Booktitle = {Proc. Conf. on Artificial Intelligence}, Date-Added = {2006-03-06 10:13:50 +0100}, Date-Modified = {2006-03-06 10:17:53 +0100}, Editor = {AAAI}, Keywords = {evaluation optimiation CSP all-different}, Pages = {362--367}, Title = {{A Filtering Algorithm for Constraints of Difference in CSPs}}, Year = {1994}, Abstract = {Many real-life Constraint Satisfaction Problems (CSPs) involve some constraints similar to the alldifferent constraints. These constraints are called constraints of difference. They are defined on a subset of variables by a set of tuples for which the values occuring in the same tuple are all different. In this paper, a new filtering algorithm for these constraints is presented. It achieves the generalized arc-consistency condition for these non-binary constraints. It is based on matching theory and its complexity is low. In fact, for a constraint defined on a subset of p variables having domains of cardinality at most d, its space complexit is O(pd) and its time complexity is O(p2d2). This filtering algorithm has been successfully used in the system RESYN, to solve the subgraph isomorphism problem.}} @book{Abiteboul_FoundationsDB_AW_1995, Address = {Boston, MA, USA}, Author = {Abiteboul, Serge and Hull, Richard and Vianu, Victor}, Date-Added = {2006-03-06 09:40:26 +0100}, Date-Modified = {2006-03-06 09:42:35 +0100}, Isbn = {0-201-53771-0}, Keywords = {database theory complexity}, Publisher = {Addison-Wesley}, Title = {{Foundations of Databases}}, Url = {http://db.bell-labs.com/user/hull/FoundDB.html}, Year = {1995}, Abstract = {This database theory book provides a focused presentation of the core material on relational databases, and presents a number of advanced topics in a unified framework. Some of the advanced material has never before been presented in book form. The style is rigorous, with detailed proofs and many exercises. The text and numerous examples highlight the intuition underlying the development. As a textbook, the book is aimed at graduate students and seniors who would use it as the main text in a database theory course, or as complementary material in a database systems course. It can also serve as a reference for database researchers and for other computer scientists interested in databases.}, Annote = {Database theory is a relative newcomer to the field of computer science. Early data management systems were based on techniques from several classical areas of computer science, ranging from hardware and operating systems to data structures and programming languages. In the early seventies, a leap of abstraction from file systems produced relational databases and its accompanying theory, with logic as the catalyst. We believe that database theory has matured--that is has emerged as an elegant and robust part of science with its own identity. As such, it embodies its own peculiar brand of wisdom that deserves to be communicated not just to insiders, but to the computer science community at large. In a nutshell, a database management system is a software system that enables the creation, maintenance, and use of large amounts of data. In contrast with many programming applications, the logical data structure--the "database schema"--used to structure a given data set is usually much smaller than the volume of that set. Furthermore, the data is persistent, evolving over time and surviving multiple invocations of the database management software. To increase usability, concurrent access to the data is usually supported with specialized protocols that guarantee a form of noninterference between interleaved transactions. Importantly, modern database management systems embody a distinction between the logical level and the physical level. The logical level focuses on an abstract representation of the data, along with languages to create, query and modify it; the physical level focuses on the underlying implementation, including the physical layout used to store the data, the indexing and clustering schemes, and the concurrency and recovery protocols. Database theory has developed primarily around the logical level of database. (A notable exception is concurrency control, which is not addressed in this volume.) A core of fundamental material on the relational model has become well established. It consists primarily of three paradigms for query languages (algebraic, calculus-based, and deductive) and the theory of dependencies. The theory of query languages, including issues of expressiveness and complexity specific to databases, is well developed. The marriage between databases and logic programming produced deductive databases, with the main focus on the deductive query languages. Dependency theory focused initially on formalizing and applying the disparate integrity constraints that commonly arise in practice, and it went on to relate constraints with query optimization and to develop a unifying perspective for them. As a field, database theory draws on several areas, including mathematical logic, complexity, and programming languages. But the database context brings with it different assumptions, perspectives, and emphases. Relations can be viewed as predicates in the sense of logic, and the relational calculus as a specialization of the first-order predicate calculus. However, the database area emphasizes finite structures and has developed the notions of "domain independence" and "safety" to capture intuitive properties related to this finitude. The questions and techniques in dependency theory borrow heavily from logic., with a focus on practically motivated, relatively weak classes of sentences. Query languages provide an interesting contrast with conventional, imperative programming languages. Query languages typically embody a set-at-a-time focus as opposed to an object-at-a-time focus. Also, they are largely declarative in nature, and failing that, are more applicative than imperative. Because of the emphasis on tractability in the face of large volumes of data, there is considerable interest in query languages that do not have full computational power, which gives rise to a rich interplay between query languages and complexity theory. Specialized notions of complexity have arisen, stemming from the practical reality of large volumes of data and the theoretical interest in different query languages. Also, the important notion of 'genericity," which captures a form of abstraction stemming from the separation of the logical and physical levels, has led to new perspectives on complexity theory, involving formalisms that circumvent the ordering of input data implicit in traditional Turing machines. Exciting new research directions have continued to emerge in database theory, stemming primarily from unanswered questions about query languages and from an interest in expanding beyond the limitations of the relational model. Current research includes investigations motivated by connections with object-orientation, artificial intelligence, and graphics interfaces. And as the database field matures, it, in turn, influences adjacent areas in computer science, notably finite model theory, programming languages, and logic programming.}} @mastersthesis{Schroeder_Algebra_DA_2005, Author = {Schroeder, Andreas}, Date-Added = {2006-03-06 09:28:01 +0100}, Date-Modified = {2006-03-06 17:49:59 +0100}, Keywords = {XML Xcerpt optimization algebra efficicency}, School = {Institute for Informatics, University of Munich}, Title = {{An Algebra and Optimization Techniques for Simulation Unification}}, Type = {{Diplomarbeit/Master thesis}}, Url = {http://www.pms.ifi.lmu.de/publikationen#DA_Andreas.Schroeder}, Year = {2005}} @techreport{Pepper_RDFTM_W3C_2006, Author = {Pepper, Steve and Vitali, Fabio and Garshol, Lars Marius and Gessa, Nicola and Presutti, Valentina}, Date-Added = {2006-03-03 08:20:34 +0100}, Date-Modified = {2006-03-03 08:21:36 +0100}, Institution = {W3C}, Keywords = {RDF Topic Maps interoperability versatility conversion}, Title = {{A Survey of RDF/Topic Maps Interoperability Proposals}}, Type = {Working Group Note}, Url = {http://www.w3.org/TR/rdftm-survey/}, Year = {2006}} @inproceedings{Furche_XMLRDF_GVD_2005, Author = {Furche, Tim and Bry, Fran{\c c}ois and Bolzer, Oliver}, Booktitle = {Proc. Workshop on Grundlagen von Datenbanken}, Date-Added = {2006-03-03 08:09:11 +0100}, Date-Modified = {2006-03-03 08:10:05 +0100}, Keywords = {XML RDF transformation integration veratility serialization}, Organization = {GI}, Title = {{XML Perspectives on RDF Querying: Towards integrated Access to Data and Metadata on the Web}}, Url = {http://www.pms.ifi.lmu.de/publikationen/#PMS-FB-2005-13}, Year = {2005}} @inproceedings{Furche_MarriagesRDF_PPSWR_2005, Author = {Furche, Tim and Bry, Fran{\c c}ois and Bolzer, Oliver}, Booktitle = {Proc. Intl. Workshop on Principles and Practice of Semantic Web Reasoning}, Date-Added = {2006-03-03 07:44:33 +0100}, Date-Modified = {2006-03-06 17:03:32 +0100}, Keywords = {RDF XML versatility triple graphs logical view}, Publisher = {Springer-Verlag}, Series = {LNCS}, Title = {{Marriages of Convenience: Triples and Graphs, RDF and XML}}, Url = {http://www.pms.ifi.lmu.de/publikationen/#PMS-FB-2005-38}, Volume = {3703}, Year = {2005}} @article{Zloof_Query-by-Example-DataBase_IBMSJ_1977, Author = {Zloof, Moshe M.}, Date-Added = {2006-03-03 06:43:18 +0100}, Date-Modified = {2006-03-03 06:44:20 +0100}, Journal = {IBM Systems Journal}, Myurl = {http://www.research.ibm.com/j ournal/sj/164/ibmsj1604C.pdf}, Number = {4}, Pages = {324--343}, Title = {{Query By Example: A Data Base Language}}, Volume = {16}, Year = {1977}, Abstract = {Discussed is a high-level data base management language that provides the user with a convenient and unified interface to query, update, define, and control a data base. When the user performs an operation against the data base, he fills in an example of a solution to that operation in skeleton tables that can be associated with actual tables in the data base. The system is currently being used experimentally for various applications.}} @techreport{Backett_Turtle_2005, Author = {Backett, Dave}, Date-Added = {2006-03-02 17:44:30 +0100}, Date-Modified = {2006-03-02 17:45:58 +0100}, Institution = {W3C}, Keywords = {RDF syntax text serialization}, Title = {{Turtle---Terse RDF Triple Language}}, Url = {http://www.w3.org/2001/sw/DataAccess/df1/}, Year = {2005}, Abstract = {he Resource Description Framework (RDF) is a general-purpose language for representing information in the Web. This document defines a text syntax for RDF called Turtle as an extension of the N-Triples ([N-TRIPLES]) test case format carefully taking the most useful and appropriate things added from Notation 3 ([NOTATION3]) while keeping the syntax describing only RDF graphs.}} @inproceedings{Beckett_Modernising_2004, Author = {Backett, Dave}, Booktitle = {Proc XML Europe}, Date-Added = {2006-03-02 17:40:54 +0100}, Date-Modified = {2006-03-02 17:41:19 +0100}, Keywords = {RDF serialization format RXR XML}, Month = {April}, Myurl = {http://www.idealliance.org/pa pers/dx_xmle04/papers/03-08-0 3/03-08-03.html}, Title = {{Modernising Semantic Web Markup}}, Year = {2004}, Annote = {The Resource Description Framework (RDF) web metadata format has an XML syntax RDF/XML which has been described as a ugly and flawed, mainly as a consequence of it being an early XML format, dating from 1998. This presentation will describe the perceived and real problems and select appropriate modern XML and web best practices for improving RDF markup that can be better used with the latest XML technologies such as XSLT 2 and XQuery. The presentation will distinguish a semantic web markup format rather than a format intended solely for software as one intended to be easier for end users to author and more clearly be appropriate for typical application areas of lightweight web metadata and authored web ontologies. XML best practice in any area is a tricky subject to discuss and get agreement on but the XML technologies considered include XML Namespaces, XML QNames in content, omitting some darker corners of the XML specification along with use of clear user-friendly technologies such as the RELAXNG grammar-based XML schema language, part of the ISO DSDL work. The presentation will also discuss approaches starting from XHTML to generate semantic web data.}} @techreport{Adida_RDFA_W3C_2006, Author = {Adida, Ben and Birbeck, Mark}, Date-Added = {2006-03-02 17:38:01 +0100}, Date-Modified = {2006-03-02 17:39:41 +0100}, Institution = {W3C}, Keywords = {RDF XHTML metadata embedding syntax serialization}, Title = {{RDF/A Primer 1.0---Embedding RDF in XHTML}}, Type = {Internal Draft}, Url = {http://www.w3.org/2001/sw/BestPractices/HTML/2006-01-24-rdfa-primer}, Year = {2006}, Abstract = {This document introduces the RDF/A syntax for expressing RDF metadata within XHTML. The reader is expected to be fairly familiar with XHTML, and somewhat familiar with RDF. This is an internal draft produced by the RDF-in-HTML task force [RDFHTML], a joint task force of the Semantic Web Best Practices and Deployment Working Group [SWBPD-WG] and HTML Working Group [HTML-WG]. This document is for internal review only and is subject to change without notice. This document has no formal standing within the W3C.}} @techreport{W3C_RDFXML_Rec_2004, Author = {Beckett, Dave and McBride, Brian}, Date-Added = {2006-03-02 17:35:56 +0100}, Date-Modified = {2006-03-02 17:36:34 +0100}, Institution = {W3C}, Keywords = {RDF syntax RDF/XML serialization}, Organization = {W3C}, Title = {{RDF/XML Syntax Specification (Revised)}}, Type = {Recommendation}, Url = {http://www.w3.org/TR/rdf-synt ax-grammar/}, Year = {2004}, Abstract = {The Resource Description Framework (RDF) is a general-purpose language for representing information in the Web. This document defines an XML syntax for RDF called RDF/XML in terms of Namespaces in XML, the XML Information Set and XML Base. The formal grammar for the syntax is annotated with actions generating triples of the RDF graph as defined in RDF Concepts and Abstract Syntax. The triples are written using the N-Triples RDF graph serializing format which enables more precise recording of the mapping in a machine processable form. The mappings are recorded as tests cases, gathered and published in RDF Test Cases.}} @techreport{W3C_XInclude_Rec_2004, Author = {Marsh, Jonathan and Orchard, David}, Date-Added = {2006-03-02 15:37:08 +0100}, Date-Modified = {2006-03-02 15:37:44 +0100}, Institution = {W3C}, Keywords = {XML inclusion transformation recommendation}, Organization = {W3C}, Title = {{XML Inclusions (XInclude) Version 1.0}}, Type = {Recommendation}, Url = {http://www.w3.org/TR/xinclude/}, Year = {2004}, Abstract = {This document specifies a processing model and syntax for general purpose inclusion. Inclusion is accomplished by merging a number of XML information sets into a single composite infoset. Specification of the XML documents (infosets) to be merged and control over the merging process is expressed in XML-friendly syntax (elements, attributes, URI references).}} @inproceedings{PatelSchneider_XMLSyntaxRDFSemantics_WWW_2002, Author = {Patel-Schneider, Peter and Simeon, Jerome}, Booktitle = {Proc. Intl. World Wide Web Conference}, Date-Added = {2006-03-02 13:25:38 +0100}, Date-Modified = {2006-03-02 13:26:39 +0100}, Keywords = {XML RDF data model semantics integration}, Month = {May}, Title = {{The Yin/Yang Web: XML Syntax and RDF Semantics}}, Url = {http://www2002.org/CDROM/refereed/231/}, Year = {2002}, Abstract = {XML is the W3C standard document format for writing and exchanging information on the Web. RDF is the W3C standard model for describing the semantics and reasoning about information on the Web. Unfortunately, RDF and XML---although very close to each other---are based on two different paradigms. We argue that in order to lead the Semantic Web to its full potential, the syntax and the semantics of information needs to work together. To this end, we develop a model-theoretic semantics for the XML XQuery 1.0 and XPath 2.0 Data Model, which provides a unified model for both XML and RDF. This unified model can serve as the basis for Web applications that deal with both data and semantics. We illustrate the use of this model on a concrete information integration scenario. Our approach enables each side of the fence to benefit from the other, notably, we show how the RDF world can take advantage of XML query languages, and how the XML world can take advantage of the reasoning capabilities available for RDF.}} @techreport{McGuiness_OWL_W3C_2004, Author = {McGuinness, Deborah L. and van Harmelen, Frank}, Date-Added = {2006-03-02 13:18:42 +0100}, Date-Modified = {2006-03-02 13:19:59 +0100}, Institution = {W3C}, Keywords = {OWL RDF ontology description logics W3C}, Title = {{OWL Web Ontology Language---Overview}}, Type = {Recommendation}, Url = {http://www.w3.org/TR/owl-features/}, Year = {2004}} @techreport{Brickley_RDFS_W3C_2004, Author = {Brickley, Dan and Guha, R.V.}, Date-Added = {2006-03-02 13:11:40 +0100}, Date-Modified = {2006-03-02 13:12:42 +0100}, Institution = {W3C}, Keywords = {RDF RDFS ontology schema vocabulary}, Title = {{RDF Vocabulary Description Language}}, Type = {Recommendation}, Url = {http://www.w3.org/TR/rdf-schema/}, Year = {2004}} @misc{Bry_ea_EfficientXcerpt_UNPUB2006, Author = {Bry, Fran{\c c}ois and Schroeder, Andreas and Furche, Tim and Linse, Benedikt}, Date-Added = {2006-02-20 15:20:10 +0100}, Date-Modified = {2006-03-06 16:42:08 +0100}, Howpublished = {Submitted for publication}, Title = {{Efficient Evaluation of n-ary Queries over Trees and Graphs}}, Year = {2006}} @inproceedings{Berger_ea_TypingXcerpt_PPSWR2005, Author = {Berger, Sacha and Coquery, Emmanuel and Drabent, W\lodzimierz and Wilk, Artur}, Booktitle = {Proc. of Workshop on Principles and Practice of Semantic Web Reasoning}, Date-Added = {2006-02-20 15:13:39 +0100}, Date-Modified = {2006-03-06 17:03:16 +0100}, Keywords = {XML xcerpt typing R2G2}, Number = {3703}, Organization = {REWERSE}, Publisher = {Springer-Verlag}, Series = {LNCS}, Title = {{Descriptive Typing Rules for Xcerpt}}, Url = {http://www.pms.ifi.lmu.de/publikationen/#PMS-FB-2005-39}, Year = {2005}} @article{Gottlob_ComplexityAcyclic_JACM2001, Address = {New York, NY, USA}, Author = {Gottlob, Georg and Leone, Nicola and Scarcello, Francesco}, Date-Added = {2006-02-01 17:33:28 +0100}, Date-Modified = {2006-02-01 17:39:49 +0100}, Doi = {http://doi.acm.org/10.1145/382780.382783}, Group = {Matrix Method}, Issn = {0004-5411}, Journal = {Journal of the ACM}, Number = {3}, Pages = {431--498}, Publisher = {ACM Press}, Title = {{The Complexity of Acyclic Conjunctive Queries}}, Url = {http://portal.acm.org/citation.cfm?id=382783}, Volume = {48}, Year = {2001}, Abstract = {This paper deals with the evaluation of acyclic Boolean conjunctive queries in relational databases. By well-known results of Yannakakis [1981], this problem is solvable in polynomial time; its precise complexity, however, has not been pinpointed so far. We show that the problem of evaluating acyclic Boolean conjunctive queries is complete for LOGCFL, the class of decision problems that are logspace-reducible to a context-free language. Since LOGCFL is contained in AC1 and NC2, the evaluation problem of acyclic Boolean conjunctive queries is highly parallelizable. We present a parallel database algorithm solving this problem with a logarithmic number of parallel join operations. The algorithm is generalized to computing the output of relevant classes of non-Boolean queries. We also show that the acyclic versions of the following well-known database and AI problems are all LOGCFL-complete: The Query Output Tuple problem for conjunctive queries, Conjunctive Query Containment, Clause Subsumption, and Constraint Satisfaction. The LOGCFL-completeness result is extended to the class of queries of bounded treewidth and to other relevant query classes which are more general than the acyclic queries.}} @inproceedings{Filiot_ComposingMonadicQueries_PLANX2006, Author = {Filiot, Emmanuel and Niehren, Joachim and Talbot, Jean-Marc and Tison, Sophie}, Booktitle = {Proc. Intl. Workshop on Programming Language Technologies for XML}, Date-Added = {2006-02-01 17:27:01 +0100}, Date-Modified = {2006-02-01 17:37:24 +0100}, Group = {Matrix Method}, Title = {{Composing Monadic Queries in Trees}}, Url = {http://www.lifl.fr/~filiot/publiprivate/Plan-X-final-version.pdf}, Year = {2006}, Abstract = {Node selection in trees is a fundamental operation to XML databases, programming languages, and information extraction. We propose a new class of querying languages to define n-ary node selection queries as compositions of monadic queries. The choice of the underlying monadic querying language is parametric. We show that compositions of monadic MSO-definable queries capture n-ary MSO-definable queries, and distinguish an MSO-complete n-ary query language that enjoys an efficient query answering algorithm.}} @inproceedings{Abraham.Chaudhari.ea_XMLQueryAlgebra_10C_2004, Author = {Abraham, Jacob and Chaudhari, Narendra S. and Prakash, Edmond C.}, Booktitle = {IEEE Int. Region 10 Conference (TENCON)}, Conference-Abbr = {TENCON}, Keywords = {XML XQuery algebra operators implementation survey}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/Abraham.Chaudhari.ea_XMLQueryAlgebra_TENCON_2004.pdf}, Title = {{XML Query Algebra Operators, and Strategies for their Implementation}}, Url = {http://www.ntu.edu.sg/home/asnarendra/lect_slides/SwatiFiles/TENCON04-Jacob.pdf}, Year = {2004}, Abstract = {For querying the XML data, XQuery is nowadays accepted as the language of choice. However, no query algebra for XML is not yet accepted widely. In this paper, we discuss the need for and progress of query algebras as well as the specific requirements of semi-structured data. Next, we introduce various algebras that have been proposed to date with a particular emphasis on Niagara Algebra. We discuss implementation of the operators in the Niagara algebra. This paper proposes an improvement to the logical view of the selection operator. We demonstrate the improvement due to our implementation by experimental results. We find that the degree of improvement depends on the nature of the XML data. The new operator is particularly better at working with data that has a large number of elements that need to be unnested in order to run a select. In addition, it shows a significant improvement in situations where a large number of elements must be evaluated to check if the selection criteria are met.}} @inproceedings{AlKhalifa.Jagadish_MultiLevelOp_CIKM_2002, Address = {New York, NY, USA}, Author = {Al-Khalifa, Shurug and Jagadish, H. V.}, Booktitle = {Proc. Int. Conf. Information and Knowledge Management}, Conference-Abbr = {CIKM}, Doi = {http://doi.acm.org/10.1145/584792.584817}, Isbn = {1-58113-492-4}, Keywords = {XML XQuery algebra selection operators granularity}, Location = {McLean, Virginia, USA}, Pages = {134--141}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/Al-Khalifa.Jagadish_Multi-levelOperatorCombination_CIKM_2002.pdf}, Publisher = {ACM Press}, Title = {{Multi-level Operator Combination in XML Query Processing}}, Url = {http://www.eecs.umich.edu/db/timber/files/cikm02.pdf}, Year = {2002}, Abstract = {A core set of efficient access methods is central to the development of any database system. In the context of an XML database, there has been considerable effort devoted to defining a good set of primitive operators and inventing efficient access methods for each individual operator. These primitive operators have been defined either at the macro-level (using a "pattern tree" to specify a selection, for example) or at the micro-level (using multiple explicit containment joins to instantiate a single XPath expression).In this paper we argue that it is valuable to consider operations at each level. We do this through a study of operator merging: the development of a new access method to implement a combination of two or more primitive operators. It is frequently the case that access methods for merged operators are superior to a pipelined execution of separate access methods for each operator. We show operator merging to be valuable at both the micro-level and the macro-level. Furthermore, we show that the corresponding merged operators are hard to reason with at the other level.Specifically, we consider the influence of projections and set operations on pattern-based selections and containment joins. We show, through both analysis and extensive experimentation, the benefits of considering these operations all together. Even though our experimental verification is only with a native XML database, we have reason to believe that our results apply equally to RDBMS-based XML query engines.}} @inproceedings{Al-Khalifa.Jagadish.ea_StructJoins_ICDE_2002, Address = {Washington, DC, USA}, Author = {Al-Khalifa, Shurug and Jagadish, H. V. and Koudas, Nick and Patel, Jignesh M. and Srivastava, Divesh and Wu, Yuqing}, Booktitle = {Proc. Int. Conf. on Data Engineering}, Conference-Abbr = {ICDE}, Keywords = {XML join processing operators algebra query optimization}, Pages = {141}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/StructuralJoins/Al-Khalifa.Jagadish.ea_StructJoins_ICDE_2002.pdf}, Publisher = {IEEE Computer Society}, Title = {{Structural Joins: A Primitive for Efficient XML Query Pattern Matching}}, Url = {http://www.eecs.umich.edu/~jignesh/publ/xmljoin-ICDE.pdf}, Year = {2002}, Abstract = {XML queries typically specify patterns of selection predicates on multiple elements that have some specified tree structured relationships. The primitive tree structured relationships are parent-child and ancestor-descendant, and finding all occurrences of these relationships in an XML database is a core operation for XML query processing.In this paper, we develop two families of structural join algorithms for this task: tree-merge and stack-tree. The tree-merge algorithms are a natural extension of traditional merge joins and the recently proposed multi-predicate merge joins, while the stack-tree algorithms have no counterpart in traditional relational join processing. We present experimental results on a range of data and queries using the TIMBER native XML query engine built on top of SHORE. We show that while, in some cases, tree-merge algorithms can have performance comparable to stack-tree algorithms, in many cases they are considerably worse. This behavior is explained by analytical results that demonstrate that, on sorted inputs, the stack-tree algorithms have worst-case I/O and CPU complexities linear in the sum of the sizes of inputs and output, while the tree-merge algorithms do not have the same guarantee.}} @inproceedings{AmerYahia.Cho.ea_MinimizingTreePat_SIGMOD_2001, Address = {New York, NY, USA}, Author = {Amer-Yahia, Sihem and Cho, SungRan and Lakshmanan, Laks V. S. and Srivastava, Divesh}, Booktitle = {Proc. ACM SIGMOD Int. Conf. on Management of Data}, Conference-Abbr = {SIGMOD}, Doi = {http://doi.acm.org/10.1145/375663.375730}, Isbn = {1-58113-332-4}, Keywords = {XML tree pattern queries minimization}, Location = {Santa Barbara, California, United States}, Pages = {497--508}, Pdf = {QueryEvaluation/XML/Containment/AmerYahia.Cho.ea_MinimizingTreePat_SIGMOD_2001.pdf}, Publisher = {ACM Press}, Title = {{Minimization of Tree Pattern Queries}}, Url = {http://portal.acm.org/citation.cfm?id=375730}, Year = {2001}, Abstract = {Tree patterns form a natural basis to query tree-structured data such as XML and LDAP. Since the efficiency of tree pattern matching against a tree-structured database depends on the size of the pattern, it is essential to identify and eliminate redundant nodes in the pattern and do so as quickly as possible. In this paper, we study tree pattern minimization both in the absence and in the presence of integrity constraints (ICs) on the underlying tree-structured database. When no ICs are considered, we call the process of minizing a tree pattern, constraint-independent minimization. We develop a polynomial time algorithm called CIM for this purpose. CIM's efficiency stems from two key properties: (i) a node cannot be redundant unless its children are, and (ii) the order of elimination of redundant nodes is immaterial. When ICs are considered for minimization, we refer to it as constraint-dependent minimization. For tree-structured databases, required child/descendant andd type co-occurrence ICs are very natural. Under such ICs, we show that the minimal equivalent query is unique. We show the surprising result that the algorithm obtained by first augmenting the tree pattern using ICs, and then applying CIM, always finds the unique minimal equivalent query; we refer to this algorithm as ACIM. While ACIM is also polynomial time, it can be expensive in practice because of its inherent non-locality. We then present a fast algorithm, CDM, that identifies and eliminates local redundancies due to ICs, based on propagating "information labels" up the tree pattern. CDM can be applied prior to ACIM for improving the minimization efficiency. We complement our analytical results with an experimental study that shows the effectiveness of our tree pattern minimization techniques.}} @inproceedings{Babcock.Chaudhuri_RobustOpti_SIGMOD_2005, __Markedentry = {0}, Address = {New York, NY, USA}, Author = {Babcock, Brian and Chaudhuri, Surajit}, Booktitle = {Proc. ACM SIGMOD Int. Conf. on Management of Dataime}, Conference-Abbr = {SIGMOD}, Doi = {http://doi.acm.org/10.1145/1066157.1066172}, Isbn = {1-59593-060-4}, Keywords = {query optimization query evaluation robustness}, Location = {Baltimore, Maryland}, Pages = {119--130}, Pdf = {QueryEvaluation/Babcock.Chaudhuri_RobustOpti_SIGMOD_2005.pdf}, Publisher = {ACM Press}, Title = {{Towards a Robust Query Optimizer: A Principled and Practical Approach}}, Url = {http://portal.acm.org/citation.cfm?id=1066157.1066172}, Year = {2005}, Abstract = {Research on query optimization has focused almost exclusively on reducing query execution time, while important qualities such as consistency and predictability have largely been ignored, even though most database users consider these qualities to be at least as important as raw performance. In this paper, we explore how the query optimization process can be made more robust, focusing on the important subproblem of cardinality estimation. The robust cardinality estimation technique that we propose allows for a user- or application-specified trade-off between performance and predictability, and it captures multi-dimensional correlations while remaining space- and time-efficient.}} @inproceedings{Babu.Bizarro.ea_ProactiveReopt_SIGMOD_2005, Author = {Babu, Shivnath and Bizarro, Pedro and DeWitt, David}, Booktitle = {Proc. ACM SIGMOD Int. Conf. on Management of Data}, Conference-Abbr = {SIGMOD}, Keywords = {XML algebra query optimization query plan}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/Babu.Bizarro.ea_ProactiveReopt_SIGMOD_2005.pdf}, Title = {{Proactive Re-Optimization}}, Url = {http://dbpubs.stanford.edu:8090/pub/2005-6}, Year = {2005}, Abstract = {Traditional query optimizers rely on the accuracy of estimated statistics to choose good execution plans. This design often leads to suboptimal plan choices for complex queries, since errors in estimates for intermediate subexpressions grow exponentially in the presence of skewed and correlated data distributions. Re-optimization is a promising technique to cope with such mistakes. Current re-optimizers first use a traditional optimizer to pick a plan, and then react to estimation errors and resulting suboptimalities detected in the plan during execution. The effectiveness of this approach is limited because traditional optimizers choose plans unaware of issues affecting re-optimization. We address this problem using proactive re-optimization, a new approach that incorporates three techniques: (1) the uncertainty in estimates of statistics is computed in the form of bounding boxes around these estimates, (2) these bounding boxes are used to pick plans that are robust to deviations of actual values from their estimates, (3) accurate measurements of statistics are collected quickly and efficiently during query execution. We present an extensive evaluation of these techniques using a prototype proactive re-optimizer named Rio. In our experiments Rio outperforms current re-optimizers by up to a factor of three.}} @inproceedings{BarYossef.Fontoura.ea_MemReqXPath_PODS_2004, Address = {New York, NY, USA}, Author = {Bar-Yossef, Ziv and Fontoura, Marcus and Josifovski, Vanja}, Booktitle = {Proc. ACM SIGMOD Symposium on Principles of Database Systems}, Conference-Abbr = {PODS}, Doi = {http://doi.acm.org/10.1145/1055558.1055584}, Isbn = {158113858X/04/06}, Keywords = {XML XPath memory complexity stream}, Location = {Paris, France}, Pages = {177--188}, Pdf = {QueryEvaluation/XML/Comlexity/BarYossef.Fontoura.ea_MemReqXPath_PODS_2004.pdf}, Publisher = {ACM Press}, Title = {{On the Memory Requirements of XPath Evaluation over XML Streams}}, Url = {http://www.ee.technion.ac.il/people/zivby/papers/xml/xmlfull.pdf}, Year = {2004}, Abstract = {The important challenge of evaluating XPath queries over XML streams has sparked much interest in the past two years, A number of algorithms have been proposed, supporting wider fragments of the query language, and exhibiting better performance and memory utilization. Nevertheless, all the algorithms known to date use a prohibitively large amount of memory for certain types of queries. A natural question then is whether this memory bottleneck is inherent or just an artifact of the proposed algorithms.In this paper we initiate the first systematic and theoretical study of lower bounds on the amount of memory required to evaluate XPath queries over XML streams. We present a general lower bound technique, which given a query, specifies the minimum amount of memory that any algorithm evaluating the query on a stream would need to incur. The lower bounds are stated in terms of new graph-theoretic properties of queries. The proof is based on tools from communication complexity.We then exploit insights learned from the lower bounds to obtain a new algorithm for XPath evaluation on streams. The algorithm uses space close to the optimum. Our algorithm deviates from the standard paradigm of using automata or transducers, thereby avoiding the need to store large transition tables.}} @inproceedings{Bayardo.Gruhl.ea_BinaryXMLStream_WWW_2004, Author = {Bayardo, Roberto J. and Gruhl, Daniel and Josifovski, Vanja and Myllymaki, Jussi}, Booktitle = {Proc. Int. World Wide Web Conf.}, Conference-Abbr = {WWW}, Doi = {http://doi.acm.org/10.1145/988672.988719}, Isbn = {1-58113-844-X}, Keywords = {XML XQuery stream binary encoding}, Location = {New York, NY, USA}, Pages = {345--354}, Pdf = {QueryEvaluation/XML/ProcessorsAndSystems/Bayardo.Gruhl.ea_BinaryXMLStream_WWW_2004.pdf}, Publisher = {ACM Press}, Title = {{An Evaluation of Binary XML Encoding Optimizations for fast Stream based XML Processing}}, Url = {http://www.www2004.org/proceedings/docs/1p345.pdf}, Year = {2004}, Abstract = {This paper provides an objective evaluation of the performance impacts of binary XML encodings, using a fast stream-based XQuery processor as our representative application. Instead of proposing one binary format and comparing it against standard XML parsers, we investigate the individual effects of several binary encoding techniques that are shared by many proposals. Our goal is to provide a deeper understanding of the performance impacts of binary XML encodings in order to clarify the ongoing and often contentious debate over their merits, particularly in the domain of high performance XML stream processing.}} @inproceedings{Beeri.Tzaban_SAL_WebDB_1999, Author = {Beeri, Catriel and Tzaban, Yariv}, Booktitle = {Proc. Int. Workshop on the Web and Databases}, Conference-Abbr = {WebDB}, Keywords = {XML SAL algebra semi-structured XAL}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/Beeri.Tzaban_SAL_WebDB_1999.pdf}, Title = {{SAL: An Algebra for Semistructured Data and XML}}, Url = {http://www-rocq.inria.fr/~cluet/WEBDB/beeri.ps}, Year = {1999}, Abstract = {--}} @article{Berlea.Seidl_BinaryQueriesDocument_NJC_2004, Author = {Berlea, Alexandru and Seidl, Helmut}, Journal = {Nordic Journal of Computing}, Journal-Abbr = {NJC}, Keywords = {XML query languages evluation binary queries fxt fxgrep}, Number = {1}, Pages = {41--71}, Pdf = {QueryEvaluation/XML/Comlexity/Berlea.Seidl_BinaryQueriesDocument_NJC_2004.pdf}, Title = {{Binary Queries for Document Trees}}, Url = {http://atseidl2.informatik.tu-muenchen.de/~berlea/publications/njc/binaries.pdf}, Volume = {11}, Year = {2004}, Abstract = {Motivated by XML applications, we address the problem of answering k-ary queries, i.e. simultaneously locating k nodes of an input tree as specified by a given relation. In particular, we discuss how binary queries can be used as a means of navigation in XML document transformations. We introduce a grammar-based approach to specifying k-ary queries. An efficient tree-automata based implementation of unary queries is reviewed and the extensions needed in order to implement k-ary queries are presented. In particular, an efficient solution for the evaluation of binary queries is provided and proven correct. We introduce fxgrep, a practical implementation of unary and binary queries for XML. By means of fxgrep and of the fxt XML transformation language we suggest how binary queries can be used in order to increase expressivity of rule-based transformations. We compare our work with other querying languages and discuss how our ideas can be used for other existing settings.}} @inproceedings{Beyer.Cochrane.ea_XQueryAnalytics_XIME-P_2004, Author = {Beyer, Kevin S. and Cochrane, Roberta and Colby, Latha S. and Ozcan, Fatma and Pirahesh, Hamid}, Booktitle = {Proc. of Int. Workshop on XQuery Implementation, Experience and Perspectives ?XIME-P/?}, Conference-Abbr = {XIME-P}, Date-Modified = {2005-05-21 17:58:53 +0200}, Keywords = {XQuery XML grouping analytics use cases group-by}, Owner = {Tim Furche}, Pages = {3-8}, Pdf = {QueryEvaluation/XML/LanguageConstructs/XQuery/Beyer.Cochrane.ea_XQueryAnalytics_XIME-P_2004.pdf}, Title = {{XQuery for Analytics: Challenges and Requirements}}, Url = {http://www-rocq.inria.fr/gemo/Gemo/Projects/XIME-P/CR/PDF/BeyerCR.pdf}, Year = {2004}, Abstract = {XML has emerged as the industry standard for representing and exchanging data and is already predominant in several applications today. Business, analytic, and structured data will be exchanged as XML between applications and web services. XQuery is a query language that is emerging as the standard for querying XML data. The current version of the XQuery standard contains many features for navigating the hierarchical and ordered content of XML data. However, as compared to SQL, it lacks some key constructs which makes it di cult to succinctly express and e ciently execute some simple classes of analytic queries. In this paper, we describe some of the limitations of the current XQuery language and argue that extensions to XQuery are necessary to overcome these limitations.}} @techreport{Boncz.Grust.ea_LoopStaircase_TR_2005, Author = {Boncz, Peter and Grust, Torsten and van Keulen, Maurice and Manegold, Stefan and Rittinger, Jan and Teubner, Jens}, Institution = {CWI}, Keywords = {XML staircase join structural join loop-lifting}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/StructuralJoins/Boncz.Grust.ea_LoopStaircase_TR_2005.pdf}, Title = {{Loop-lifted Staircase Join: from XPath to XQuery}}, Url = {http://www.inf.uni-konstanz.de/~rittinge/publications/INS-E0510.pdf}, Year = {2005}, Abstract = {Various techniques have been proposed for efficient evaluation of XPath expressions, where the XPath location steps are rooted in a single sequence of context nodes. Among these techniques, the staircase join allows to evaluate XPath location steps along arbitrary axes in at most one scan over the XML document, exploiting the XPath accelerator encoding (aka. pre/post encoding). In XQuery, however, embedded XPath sub-expressions occur in arbitrarily nested for-loops. Thus, they are rooted in multiple sequences of context nodes (one per iteration). Consequently, the previously proposed algorithms need to be applied repeatedly, requiring multiple scans over the XML document encoding. In this work, we present loop-lifted staircase join, an extension of the staircase join that allows to efficiently evaluate XPath sub-expressions in arbitrarily nested XQuery iteration scopes with only a single scan over the document. We implemented the loop-lifted staircase join in MonetDB/XQuery, that uses the XQuery-to-Relational Algebra compiler Pathfinder on top of the extensible RDBMS MonetDB. Performance results indicate that the proposed technique allows to build a system that is capable of efficiently evaluating XQuery queries including embedded XPath expressions, obtaining interactive query execution times for all XMark queries even on multi-gigabyte XML documents.}} @techreport{Boncz.Grust.ea_Pathfinder_TR_2005, Address = {Amsterdam, The Netherlands}, Author = {Boncz, Peter and Grust, Torsten and Manegold, Stefan and Rittinger, Jan and Teubner, Jens}, Institution = {CWI}, Keywords = {XML Pathfinder joins relational implementation}, Number = {INS-E0503}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/ProcessorsAndSystems/Boncz.Grust.ea_Pathfinder_TR_2005.pdf}, Title = {{Pathfinder: Relational XQuery Over Multi-Gigabyte XML Inputs In Interactive Time}}, Url = {http://www.inf.uni-konstanz.de/~rittinge/publications/INS-E0503.pdf}, Year = {2005}, Abstract = {Pathfinder/MonetDB is a collaborative effort of the University of Konstanz, the University of Twente, and the Centrum voor Wiskunde en Informatica (CWI) in Amsterdam to develop an XQuery compiler that targets an RDBMS back-end. The author of this abstract is student at the University of Konstanz and spent six months as an intern at the CWI, designing and implementing a translation of XQuery Core to (a variant of) relational algebra. His work continues in the research group at the University of Konstanz.}} @inproceedings{Bothner_XQuery2Java_XIME-P_2004, Author = {Bothner, Per}, Booktitle = {Proc. of Int. Workshop on XQuery Implementation, Experience and Perspectives }, Conference-Abbr = {XIME-P}, Keywords = {XML XQuery Bytecode Java translation}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/ProcessorsAndSystems/Translating/Bothner_XQuery2Java_XIME-P_2004.pdf}, Title = {{Compiling XQuery to Java Bytecodes}}, Url = {http://per.bothner.com/papers/Qexo04/}, Year = {2004}, Abstract = {--}} @inproceedings{Brantner.Helmer.ea_AlgebraicXPath_ICDE_2005, Address = {Washington, DC, USA}, Author = {Brantner, Matthias and Helmer, Sven and Kanne, Carl-Christian and Moerkotte, Guido}, Booktitle = {Proc. Inst. Conf. on Data Engineering}, Conference-Abbr = {ICDE}, Doi = {http://dx.doi.org/10.1109/ICDE.2005.69}, Isbn = {0-7695-2285-8}, Keywords = {XML native database algebra natix XPath}, Pages = {705--716}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/Brantner.Helmer.ea_Full-FledgedAlgebraicXPath_ICDE_2005.pdf}, Publisher = {IEEE Computer Society}, Title = {{Full-Fledged Algebraic XPath Processing in Natix}}, Url = {http://pi3.informatik.uni-mannheim.de/publications/xpath_icde2005.pdf}, Year = {2005}, Abstract = {We present the first complete translation of XPath into an algebra, paving the way for a comprehensive, state-of-the-art XPath (and later on, XQuery) compiler based on algebraic optimization techniques. Our translation includes all XPath features such as nested expressions, position-based predicates and node-set functions. The translated algebraic expressions can be executed using the proven, scalable, iterator-based approach, as we demonstrate in form of a corresponding physical algebra in our native XML DBMS Natix. A first glance at performance results shows that even without further optimization of the expressions, we provide a competitive evaluation technique for XPath queries.}} @inproceedings{Brantner.Kanne.ea_CostReorderNavi_SIGMOD_2005, Author = {Brantner, Matthias and Kanne, Carl-Christian and Moerkotte, Guido}, Booktitle = {Proc. ACM SIGMOD Int. Conf. on Management of Data}, Conference-Abbr = {SIGMOD}, Keywords = {XML XPath query optimization Natix navigational reordering}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/Brantner.Kanne.ea_CostReorderNavi_SIGMOD_2005.pdf}, Title = {{Cost-Sensitive Reordering of Navigational Primitives}}, Url = {http://pi3.informatik.uni-mannheim.de/publications/xassembly_sigmod2005.pdf}, Year = {2005}, Abstract = {We present a method to evaluate path queries based on the novel concept of partial path instances. Our method (1) maximizes performance by means of sequential scans or asynchronous I/O, (2) does not require a special storage format, (3) relies on simple navigational primitives on trees, and (4) can be complemented by existing logical and physical optimizations such as duplicate elimination, duplicate prevention and path rewriting. We use a physical algebra which separates those navigation operations that require I/O from those that do not. All I/O operations necessary for the evaluation of a path are isolated in a single operator, which may employ ef cient I/O scheduling strategies such as sequential scans or asynchronous I/O. Performance results for queries from the XMark benchmark show that reordering the navigation operations can increase performance up to a factor of four.}} @inproceedings{Bruno.Maitre.ea_ExtXQueryTransform_DocEng_2003, Author = {Bruno, Emmanuel and Maitre, Jacques Le and Murisasco, Elisabeth}, Booktitle = {Proc. ACM symposium on Document Engineering}, Conference-Abbr = {DocEng}, Date-Modified = {2005-05-21 18:05:17 +0200}, Doi = {http://doi.acm.org/10.1145/958220.958223}, Isbn = {1-58113-724-9}, Keywords = {XML XQuery transformations document engineering query languages}, Location = {Grenoble, France}, Pages = {1--8}, Pdf = {QueryEvaluation/XML/LanguageConstructs/XQuery/Bruno.Maitre.ea_ExtXQueryTransform_DocEng_2003.pdf}, Publisher = {ACM Press}, Title = {{Extending XQuery with Transformation Operators}}, Url = {http://www.univ-tln.fr/~lemaitre/doceng2003.pdf}, Year = {2003}, Abstract = {In this paper, we propose to extend XQuery - the XML query language - with a set of transformation operators which will produce a copy of an XML tree in which some subtrees will be inserted, replaced or deleted. These operators - very similar to the ones proposed for updating an XML document - greatly simplify the expression of some queries in making it possible to express only the modified part of a tree instead of its whole reconstruction. We compare the expressivity of XQuery extended in this way with XSLT.}} @inproceedings{Bruno.Koudas.ea_HolisticTwigJoins_SIGMOD_2002, Address = {New York, NY, USA}, Author = {Bruno, Nicolas and Koudas, Nick and Srivastava, Divesh}, Booktitle = {Proc. ACM SIGMOD Int. Conf. on Management of Data}, Conference-Abbr = {SIGMOD}, Doi = {http://doi.acm.org/10.1145/564691.564727}, Isbn = {1-58113-497-5}, Keywords = {XML structural joins twig joins query optimization pattern matching}, Location = {Madison, Wisconsin}, Pages = {310--321}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/StructuralJoins/Bruno.Koudas.ea_HolisticTwigJoins_SIGMOD_2002.pdf}, Publisher = {ACM Press}, Title = {{Holistic Twig Joins: Optimal XML Pattern Matching}}, Url = {http://www.research.att.com/~divesh/papers/bks2002-twigjoin.pdf}, Year = {2002}, Abstract = {XML employs a tree-structured data model, and, naturally, XML queries specify patterns of selection predicates on multiple elements related by a tree structure. Finding all occurrences of such a twig pattern in an XML database is a core operation for XML query processing. Prior work has typically decomposed the twig pattern into binary structural (parent-child and ancestor-descendant) relationships, and twig matching is achieved by: (i) using structural join algorithms to match the binary relationships against the XML database, and (ii) stitching together these basic matches. A limitation of this approach for matching twig patterns is that intermediate result sizes can get large, even when the input and output sizes are more manageable.In this paper, we propose a novel holistic twig join algorithm, TwigStack, for matching an XML query twig pattern. Our technique uses a chain of linked stacks to compactly represent partial results to root-to-leaf query paths, which are then composed to obtain matches for the twig pattern. When the twig pattern uses only ancestor-descendant relationships between elements, TwigStack is I/O and CPU optimal among all sequential algorithms that read the entire input: it is linear in the sum of sizes of the input lists and the final result list, but independent of the sizes of intermediate results. We then show how to use (a modification of) B-trees, along with TwigStack, to match query twig patterns in sub-linear time. Finally, we complement our analysis with experimental results on a range of real and synthetic data, and query twig patterns.}} @article{Buneman.Fernandez.ea_UnQL_VLDBJ_2000, Address = {Secaucus, NJ, USA}, Author = {Buneman, Peter and Fernandez, Mary and Suciu, Dan}, Doi = {http://dx.doi.org/10.1007/s007780050084}, Issn = {1066-8888}, Journal = {VLDB Journal}, Journal-Abbr = {VLDBJ}, Keywords = {XML UnQL algebra query language query optimization structural recursion}, Number = {1}, Pages = {76--110}, Pdf = {QueryEvaluation/XML/LanguageConstructs/Buneman.Fernandez.ea_UnQL_VLDBJ_2000.pdf}, Publisher = {Springer-Verlag New York, Inc.}, Title = {{UnQL: a query language and algebra for semistructured data based on structural recursion}}, Url = {http://portal.acm.org/citation.cfm?id=765224}, Volume = {9}, Year = {2000}, Abstract = {This paper presents structural recursion as the basis of the syntax and semantics of query languages for semistructured data and XML. We describe a simple and powerful query language based on pattern matching and show that it can be expressed using structural recursion, which is introduced as a top-down, recursive function, similar to the way XSL is defined on XML trees. On cyclic data, structural recursion can be defined in two equivalent ways: as a recursive function which evaluates the data top-down and remembers all its calls to avoid infinite loops, or as a bulk evaluation which processes the entire data in parallel using only traditional relational algebra operators. The latter makes it possible for optimization techniques in relational queries to be applied to structural recursion. We show that the composition of two structural recursion queries can be expressed as a single such query, and this is used as the basis of an optimization method for mediator systems. Several other formal properties are established: structural recursion can be expressed in first-order logic extended with transitive closure; its data complexity is PTIME; and over relational data it is a conservative extension of the relational calculus. The underlying data model is based on value equality, formally defined with bisimulation. Structural recursion is shown to be invariant with respect to value equality.}} @inproceedings{Calvanese.Giacomo.ea_ContainCRPQI_KR_2000, Author = {Calvanese, Diego and Giacomo, Giuseppe De and Lenzerini, Maurizio and Vardi, Moshe Y.}, Booktitle = {Proc. Int. Conf. on the Principles of Knowledge Representation and Reasoning}, Conference-Abbr = {KR}, Keywords = {query processing containment path expressions inverse conjunctive}, Pages = {176--185}, Pdf = {QueryEvaluation/XML/Containment/Calvanese.Giacomo.ea_ContainCRPQI_KR_2000.pdf}, Title = {{Containment of Conjunctive Regular Path Queries with Inverse}}, Url = {http://www.inf.unibz.it/%7ecalvanese/papers/calv-degi-lenz-vard-KR-2000.ps.gz}, Year = {2000}, Abstract = {Reasoning on queries is a basic problem both in knowledge representation and databases. A fundamental form of reasoning on queries is checking containment, i.e., verifying whether one query yields necessarily a subset of the result of another query. Query containment is crucial in several contexts, such as query optimization, knowledge base verification, information integration, database integrity checking, and cooperative answering. In this paper we address the problem of query containment in the context of semistructured knowledge bases, where the basic querying mechanism, namely regular path queries, asks for all pairs of objects that are connected by a path conforming to a regular expression. We consider conjunctive regular path queries with inverse, which extend regular path queries with the possibility of using both the inverse of binary relations, and conjunctions of atoms, where each atom specifies that one regular path query with inverse holds between two variables. We present a novel technique to check containment of queries in this class, based on the use of two-way finite automata. The technique shows the power of two-way automata in dealing with the inverse operator and with the variables in the queries. We also characterize the computational complexity of both the proposed algorithm and the problem.}} @inproceedings{Calvanese.Giacomo.ea_ViewsRPQI_PODS_2000, Author = {Calvanese, Diego and Giacomo, Giuseppe De and Lenzerini, Maurizio and Vardi, Moshe Y.}, Booktitle = {Proc. ACM SIGMOD Principles of Databases Symposium}, Conference-Abbr = {PODS}, Keywords = {conjunctive queries query languages regular path expressions inverse views optimization}, Pages = {58--66}, Pdf = {QueryEvaluation/XML/Containment/Calvanese.Giacomo.ea_ViewsRPQI_PODS_2000.pdf}, Title = {{Query Processing using Views for Regular Path Queries with Inverse}}, Url = {http://www.inf.unibz.it/%7ecalvanese/papers/calv-degi-lenz-vard-PODS-2000.ps.gz}, Year = {2000}, Abstract = {Query processing using views is the problem of computing the answer to a query based on a set of materialized views, rather than on the raw data in the database. The problem comes in two different forms, called query rewriting and query answering, respectively. In the first form, we are given a query and a set of view definitions, and the goal is to reformulate the query into an expression that refers only to the views. In the second form, besides the query and the view definitions, we are also given the extensions of the views and a tuple, and the goal is to check whether the knowledge on the view extensions logically implies that the tuple satisfies the query. In this paper we address the problem of query processing using views in the context of semistructured data, in particular for the case of regular path queries extended with the inverse operator. Several authors point out that the inverse operator is one of the fundamental extensions for making regular path queries useful in real settings. We present a novel technique based on the use of two-way finite automata. Our approach demonstrates the power of this kind of automata in dealing with the inverse operator, allowing us to show that both query rewriting and query answering with the inverse operator has the same computational complexity as for the case of standard regular path queries.}} @inproceedings{Catania.Wang.ea_LazyXML_SIGMOD_2005, Author = {Catania, Barbara and Wang, Wenqiang and Ooi, Beng Chin and Wang, Xiaoling}, Booktitle = {Proc. ACM SIGMOD Int. Conf. on Management of Data}, Conference-Abbr = {SIGMOD}, Keywords = {XML updates structural join laziness query optimization}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/NestedQueries/Catania.Wang.ea_LazyXML_SIGMOD_2005.pdf}, Title = {{Lazy XML Updates: Laziness as a Virtue of Update and Structural Join Efficiency}}, Url = {http://www.comp.nus.edu.sg/~ooibc/sigmod386.pdf}, Year = {2005}, Abstract = {XML documents are normally stored as plain text files. Hence, the natural and most convenient way to update XML documents is to simply edit the text files. But efficient query evaluation algorithms require XML documents to be in- dexed. Every element is given a unique identifier based on its location in the document or its preorder-traversal order, and this identifier is later used as (part of) the key in the index. Reassigning orders of possibly a large number of elements is therefore necessary when the original XML documents are updated. Immutable dynamic labeling schemes have been proposed to solve this problem, that, however, require very long labels and may decrease query performance. If we con- sider a real-world scenario, we note that many relatively small ad-hoc XML segments are inserted/deleted into/from an existing XML database. In this paper, we start from this consideration and we propose a new lazy approach to handle XML updates that also improves query performance. The lazy approach: (i) completely avoids reassigning existing el- ement orders after updates; (ii) improves query processing by taking advantages from segments. Experimental results show that our approach is much more efficient in handling updates than using immutable labeling and, at the same time, it also improves the performance of recently defined structural join algorithms.}} @inproceedings{Chan.Fan.ea_TamingXPathQueries_VLDB_2004, Author = {Chan, Chee-Yong and Fan, Wenfei and Zeng, Yiming}, Booktitle = {Proc. Int. Conf. on Very Large Databases}, Conference-Abbr = {VLDB}, Keywords = {XML query rewriting query optimization XPath}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/Containment/Chan.Fan.ea_TamingXPathQueries_VLDB_2004.pdf}, Title = {{Taming XPath Queries by Minimizing Wildcard Steps}}, Url = {http://www.vldb.org/conf/2004/RS4P4.PDF}, Year = {2004}, Abstract = {This paper presents a novel and complementary technique to optimize an XPath query by minimizing its wildcard steps. Our approach is based on using a general composite axis called the layer axis, to rewrite a sequence of XPath steps (all of which are wildcard steps except for possibly the last) into a single layer-axis step. We describe an efficient implementation of the layer axis and present a novel and efficient rewriting algorithm to minimize both non-branching as well as branching wildcard steps in XPath queries. We also demonstrate the usefulness of wildcard-step elimination by proposing an optimized evaluation strategy for wildcard-free XPath queries that enables selective loading of only the relevant input XML data for query evaluation. Our experimental results not only validate the scalability and efficiency of our optimized evaluation strategy, but also demonstrate the effectiveness of our rewriting algorithm for minimizing wildcard steps in XPath queries. To the best of our knowledge, this is the first effort that addresses this new optimization problem.}} @inproceedings{Chen.Rundensteiner_XQueryVar_WWW_2005, Address = {New York, NY, USA}, Author = {Chen, Li and Rundensteiner, Elke A.}, Booktitle = {Proc. Int. World Wide Web Conf.}, Conference-Abbr = {WWW}, Doi = {http://doi.acm.org/10.1145/1060745.1060789}, Isbn = {1-59593-046-9}, Keywords = {XML containment XQuery variables}, Location = {Chiba, Japan}, Pages = {288--297}, Pdf = {QueryEvaluation/XML/Containment/Chen.Rundensteiner_XQueryVar_WWW_2005.pdf}, Publisher = {ACM Press}, Title = {{XQuery Containment in Presence of Variable Binding Dependencies}}, Year = {2005}, Abstract = {Semantic caching is an important technology for improving the response time of future user queries specified over remote servers. This paper deals with the fundamental query containment problem in an XQuery-based semantic caching system. To our best knowledge, the impact of subtle differences in XQuery semantics caused by different ways of specifying variables on query containment has not yet been studied. We introduce the concept of variable binding dependencies for representing the hierarchical element dependencies preserved by an XQuery. We analyze the problem of XQuery containment in the presence of such dependencies. We propose a containment mapping technique for nested XQuery in presence of variable binding dependencies. The implication of the nested block structure on XQuery containment is also considered. We mention the performance gains achieved by a semantic caching system we build based on the proposed technique.}} @inproceedings{Chen.Rundensteiner_ACEXQ_WebDB_2002, Author = {Chen, Li and Rundensteiner, Elke A.}, Booktitle = {Proc. Workshop on the Web and Databases}, Conference-Abbr = {WebDB}, Keywords = {XML XQuery views processing evaluation}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/Containment/Chen.Rundensteiner_ACEXQ_WebDB_2002.pdf}, Title = {{ACE-XQ: A CachE-aware XQuery Answering System}}, Url = {http://www.cs.wpi.edu/~lichen/papers/webdb02-acexq.ps}, Year = {2002}, Abstract = {Caching popular queries and reusing results of these previously computed queries to speed up query processing is one important query optimization technique for distributed environments such as the Web. However, exisiting query-based cache systems, based on query containment and rewriting techniques developed for relational queries, are not appropriate for supporting more powerful XML queries. We hence propose the first solution for XML query processing using cached XQuery views. In particular, we describe in this paper an XQuery-based semantic caching system called ACE-XQ, that we have implemented to realize the proposed containment mapping and query rewriting techniques. Preliminary experiments confirm the feasibility of our approach and also illustrate the performance gains achievable by ACE-XQ over the original XQuery engine.}} @inproceedings{Chen.Lu.ea_BoostingHolism_SIGMOD_2005, Address = {New York, NY, USA}, Author = {Chen, Ting and Lu, Jiaheng and Ling, Tok Wang}, Booktitle = {Proc. ACM SIGMOD Int. Conf. on Management of Data}, Conference-Abbr = {SIGMOD}, Doi = {http://doi.acm.org/10.1145/1066157.1066209}, Isbn = {1-59593-060-4}, Keywords = {XML XPath holistic joins twig joins structural joins}, Location = {Baltimore, Maryland}, Pages = {455--466}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/StructuralJoins/Chen.Lu.ea_BoostingHolism_SIGMOD_2005.pdf}, Publisher = {ACM Press}, Title = {{On Boosting Holism in XML Twig Pattern Matching using Structural Indexing Techniques}}, Url = {http://portal.acm.org/citation.cfm?id=1066157.1066209}, Year = {2005}, Abstract = {Searching for all occurrences of a twig pattern in an XML document is an important operation in XML query processing. Recently a holistic method TwigStack. [2] has been proposed. The method avoids generating large intermediate results which do not contribute to the final answer and is CPU and I/O optimal when twig patterns only have ancestor-descendant relationships. Another important direction of XML query processing is to build structural indexes [3][8][13][15] over XML documents to avoid unnecessary scanning of source documents. We regard XML structural indexing as a technique to partition XML documents and call it streaming scheme in our paper. In this paper we develop a method to perform holistic twig pattern matching on XML documents partitioned using various streaming schemes. Our method avoids unnecessary scanning of irrelevant portion of XML documents. More importantly, depending on different streaming schemes used, it can process a large class of twig patterns consisting of both ancestor-descendant and parent-child relationships and avoid generating redundant intermediate results. Our experiments demonstrate the applicability and the performance advantages of our approach.}} @inproceedings{Chen.Davidson.ea_BLAS_SIGMOD_2004, Address = {New York, NY, USA}, Author = {Chen, Yi and Davidson, Susan B. and Zheng, Yifeng}, Booktitle = {Proc. ACM SIGMOD Int. Conf. on Management of data}, Conference-Abbr = {SIGMOD}, Doi = {http://doi.acm.org/10.1145/1007568.1007577}, Isbn = {1-58113-859-8}, Keywords = {XML XPath BLAS labelling indexing query optimization}, Location = {Paris, France}, Pages = {47--58}, Pdf = {QueryEvaluation/XML/IndexingLabelling/Chen.Davidson.ea_BLAS_SIGMOD_2004.pdf}, Publisher = {ACM Press}, Title = {{BLAS: An Efficient XPath Processing System}}, Url = {http://www.cis.upenn.edu/~yicn/blas.pdf}, Year = {2004}, Abstract = {We present BLAS, a Bi-LAbeling based System, for efficiently processing complex XPath queries over XML data. BLAS uses P-labeling to process queries involving consecutive child axes, and D-labeling to process queries involving descendant axes traversal. The XML data is stored in labeled form, and indexed to optimize descendent axis traversals. Three algorithms are presented for translating complex XPath queries to SQL expressions, and two alternate query engines are provided. Experimental results demonstrate that the BLAS system has a substantial performance improvement compared to traditional XPath processing using D-labeling.}} @inproceedings{Chen.Jagadish.ea_GeneralizedTreePats_VLDB_2003, Author = {Chen, Zhimin and Jagadish, H. V. and Lakshmanan, Laks V.S. and Paparizos, Stelios}, Booktitle = {Proc. Int. Conf. on Very Large Databases}, Conference-Abbr = {VLDB}, Keywords = {XML XQuery optimization generalized tree patterns nested queries}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/Chen.Jagadish.ea_GeneralizedTreePats_VLDB_2003.pdf}, Title = {{From Tree Patterns to Generalized Tree Patterns: On Efficient Evaluation of XQuery}}, Url = {http://www.vldb.org/conf/2003/papers/S08P03.pdf}, Year = {2003}, Abstract = {XQuery is the de facto standard XML query language, and it is important to have e cient query evaluation techniques available for it. A core operation in the evaluation of XQuery is the nding of matches for speci ed tree patterns, and there has been much work towards algorithms for nding such matches e ciently. Multiple XPath expressions can be evaluated by computing one or more tree pattern matches. However, relatively little has been done on e - cient evaluation of XQuery queries as a whole. In this paper, we argue that there is much more to XQuery evaluation than a tree pattern match. We propose a structure called generalized tree pat- tern (GTP) for concise representation of a whole XQuery expression. Evaluating the query reduces to nding matches for its GTP. Using this idea we develop e cient evaluation plans for XQuery expressions, possibly involving join, quanti ers, grouping, aggregation, and nesting. XML data often conforms to a schema. We show that using relevant constraints from the schema, one can optimize queries signi cantly, and give algorithms for automatically inferring GTP simpli cations given a schema. Finally, we show, through a detailed set of experiments using the TIMBER XML database system, that plans via GTPs (with or without schema knowledge) signi cantly outperform plans based on navigation and straightforward plans obtained directly from the query.}} @article{Christophides.ea_QueryStructured_SIGR_1994, Address = {New York, NY, USA}, Author = {Christophides, V. and Abiteboul, S. and Cluet, S. and Scholl, M.}, Doi = {http://doi.acm.org/10.1145/191843.191901}, Issn = {0163-5808}, Journal = {SIGMOD Record}, Journal-Abbr = {SIGR}, Keywords = {XML semi-structured data query path expressions O2SQL path variables}, Number = {2}, Pages = {313--324}, Pdf = {QueryEvaluation/XML/LanguageConstructs/PathVariables/Christophides.Abiteboul.ea_StructuredDocsQuery_SIGR_1994.pdf}, Publisher = {ACM Press}, Title = {{From Structured Documents to Novel Query Facilities}}, Url = {http://portal.acm.org/citation.cfm?id=191843.191901}, Volume = {23}, Year = {1994}, Abstract = {Structured documents (e.g., SGML) can benefit a lot from database support and more specifically from object-oriented database (OODB) management systems. This paper describes a natural mapping from SGML documents into OODB's and a formal extension of two OODB query languages (one SQL-like and the other calculus) in order to deal with SGML document retrieval.Although motivated by structured documents, the extensions of query languages that we present are general and useful for a variety of other OODB applications. A key element is the introduction of paths as first class citizens. The new features allow to query data (and to some extent schema) without exact knowledge of the schema in a simple and homogeneous fashion.}} @inproceedings{Cohen.Halperin.ea_Reachability2Hop_SODA_2002, Address = {Philadelphia, PA, USA}, Author = {Cohen, Edith and Halperin, Eran and Kaplan, Haim and Zwick, Uri}, Booktitle = {Proc. ACM Symposium on Discrete Algorithms}, Conference-Abbr = {SODA}, Isbn = {0-89871-513-X}, Keywords = {transitive closure reachability graph 2-hop labelling indexing}, Location = {San Francisco, California}, Pages = {937--946}, Pdf = {QueryEvaluation/XML/IndexingLabelling/Cohen.Halperin.ea_Reachability2Hop_SODA_2002.pdf}, Publisher = {Society for Industrial and Applied Mathematics}, Title = {{Reachability and Distance Queries via 2-hop Labels}}, Url = {http://portal.acm.org/citation.cfm?id=545381.545503}, Year = {2002}, Abstract = {Reachability and distance queries in graphs are fundamental to numerous applications, ranging from geographic navigation systems to Internet routing. Some of these applications involve huge graphs and yet require fast query answering. We propose a new data structure for representing all distances in a graph. The data structure is distributed in the sense that it may be viewed as assigning labels to the vertices, such that a query involving vertices u and v may be answered using only the labels of u and v.Our labels are based on 2-hop covers of the shortest paths, or of all paths, in a graph. For shortest paths, such a cover is a collection S of shortest paths such that for every two vertices u and v, there is a shortest path from u to v that is a concatenation of two paths from S. We describe an efficient algorithm for finding an almost optimal 2-hop cover of a given collection of paths. Our approach is general and can be applied to directed or undirected graphs, exact or approximate shortest paths, or to reachability queries.We study the proposed data structure using a combination of theoretical and experimental means. We implemented our algorithm and checked the size of the resulting data structure on several real-life networks from different application areas. Our experiments show that the total size of the labels is typically not much larger than the network itself, and is usually considerably smaller than an explicit representation of the transitive closure of the network.}} @inproceedings{Cohen.Kaplan.ea_LabelingDynamicXML_PODS_2002, Address = {New York, NY, USA}, Author = {Cohen, Edith and Kaplan, Haim and Milo, Tova}, Booktitle = {Proc. ACM SIGMOD Symposium on Principles of Database Systems}, Conference-Abbr = {PODS}, Doi = {http://doi.acm.org/10.1145/543613.543648}, Isbn = {1-58113-507-6}, Keywords = {XML labeling indexing dynamic 2-hop reachability}, Location = {Madison, Wisconsin}, Pages = {271--281}, Pdf = {QueryEvaluation/XML/IndexingLabelling/Cohen.Kaplan.ea_LabelingDynamicXML_PODS_2002.pdf}, Publisher = {ACM Press}, Title = {{Labeling Dynamic XML Trees}}, Url = {http://portal.acm.org/citation.cfm?id=543648}, Year = {2002}, Abstract = {We present algorithms to label the nodes of an XML tree which is subject to insertions and deletions of nodes. The labeling is done such that (1) we label each node immediately when it is inserted and this label remains unchanged, and (2) from a pair of labels alone, we can decide whether one node is an ancestor of the other. This problem arises in the context of XML databases that support queries on the structure of the documents as well us on the changes made to the documents over time. We prove that our algorithms assign the shortest possible labels (up to a constant factor) which satisfy these requirements.We also consider the same problem when "clues" that provide guarantees on possible future insertions are given together with newly inserted nodes. Such clues can be derived from the DTD or from statistics on similar XML trees. We present algorithms that use the clues to assign shorter labels. We also prove that the length of our labels is close to the minimum possible.}} @inproceedings{Cooper.Sample.ea_FastIndexSSD_VLDB_2001, Address = {San Francisco, CA, USA}, Author = {Cooper, Brian and Sample, Neal and Franklin, Michael J. and Hjaltason, Gisli R. and Shadmon, Moshe}, Booktitle = {Proc. Int. Conf. on Very Large Databases}, Conference-Abbr = {VLDB}, Isbn = {1-55860-804-4}, Keywords = {XML semi-structured data index fast}, Pages = {341--350}, Pdf = {QueryEvaluation/XML/IndexingLabelling/Cooper.Sample.ea_FastIndexSSD_VLDB_2001.pdf}, Publisher = {Morgan Kaufmann Publishers Inc.}, Title = {{A Fast Index for Semistructured Data}}, Url = {http://www.vldb.org/conf/2001/P341.pdf}, Year = {2001}, Abstract = {Queries navigate semistructured data via path expressions, and can be accelerated using an index. Our solution encodes paths as strings, and inserts those strings into a special index that is highly optimized for long and complex keys. We describe the Index Fabric, an indexing structure that provides the efficiency and flexibility we need. We discuss how "raw paths" are used to optimize ad hoc queries over semistructured data, and how "refined paths" optimize specific access paths. Although we can use knowledge about the queries and structure of the data to create refined paths, no such knowledge is needed for raw paths. A performance study shows that our techniques, when implemented on top of a commercial relational database system, outperform the more traditional approach of using the commercial system?s indexing mechanisms to query the XML.}} @inproceedings{DeHaan.Toman.ea_XQuery2SQL_SIGMOD_2003, Author = {DeHaan, David and Toman, David and Consens, Mariano P. and {\"O}zsu, M. Tamer}, Booktitle = {Proc. ACM SIGMOD Int. Conf. on Data Management}, Conference-Abbr = {SIGMOD}, Doi = {http://doi.acm.org/10.1145/872757.872832}, Isbn = {1-58113-634-X}, Keywords = {XML XQuery relational implementation tree encoding dynamic interval encoding}, Location = {San Diego, California}, Pages = {623--634}, Pdf = {QueryEvaluation/XML/ProcessorsAndSystems/Translating/DeHaan.Toman.ea_XQuery2SQL_SIGMOD_2003.pdf}, Publisher = {ACM Press}, Title = {{A Comprehensive XQuery to SQL Translation using Dynamic Interval Encoding}}, Url = {http://db.uwaterloo.ca/~david/cs848/toman-et-al-sigmod.pdf}, Year = {2003}, Abstract = {The W3C XQuery language recommendation, based on a hierarchical and ordered document model, supports a wide variety of constructs and use cases. There is a diversity of approaches and strategies for evaluating XQuery expressions, in many cases only dealing with limited subsets of the language. In this paper we describe an implementation approach that handles XQuery with arbitrarily-nested FLWR expressions, element constructors and built-in functions (including structural comparisons). Our proposal maps an XQuery expression to a single equivalent SQL query using a novel dynamic interval encoding of a collection of XML documents as relations, augmented with information tied to the query evaluation environment. The dynamic interval technique enables (suitably enhanced) relational engines to produce predictably good query plans that do not preclude the use of sort-merge join query operators. The benefits are realized despite the challenges presented by intermediate results that create arbitrary documents and the need to preserve document order as prescribed by semantics of XQuery. Finally, our experimental results demonstrate that (native or relational) XML systems can benefit from the above technique to avoid a quadratic scale up penalty that effectively prevents the evaluation of nested FLWR expressions for large documents.}} @inproceedings{Deutsch.Papakonst.ea_NestedQueries_ICDE_2004, Author = {Deutsch, Alin and Papakonstantinou, Yannis and Xu, Yu}, Bibsource = {DBLP, http://dblp.uni-trier.de}, Booktitle = {Proc. Int. Conf. on Data Engineering}, Conference-Abbr = {ICDE}, Crossref = {DBLP:conf/icde/2004}, Ee = {http://csdl.computer.org/comp/proceedings/icde/2004/2065/00/20650839.pdf}, Keywords = {XML XQuery query optimization algebra query unnesting}, Pages = {839}, Pdf = {QueryEvaluation/XML/NestedQueries/Deutsch.Papakonst.ea_NestedQueries_ICDE_2004.pdf}, Title = {{Minimization and Group-By Detection for Nested XQueries}}, Url = {http://www.db.ucsd.edu/CSE232BS03/nested-xquery-minimization.pdf}, Year = {2004}, Abstract = {We describe and evaluate a query minimization technique that applies to XQueries, which are nested, perform arbi- trary joins, and freely mix bag and set semantics. These features create key challenges that fundamentally extend the problem of minimizing conjunctive queries (no nesting, no mixed semantics) or tree pattern XPath expressions (no nesting, no joins, no bag semantics). The technique detects and removes redundant navigation across and within nested subqueries. An important application of this technique is group-by detection.}} @inproceedings{Deutsch.Papakonstantinou.ea_NEXT_VLDB_2004a, Author = {Deutsch, Alin and Papakonstantinou, Yannis and Xu, Yu}, Bibsource = {DBLP, http://dblp.uni-trier.de}, Booktitle = {Proc. Int. Conf. on Very Large Databases}, Conference-Abbr = {VLDB}, Crossref = {DBLP:conf/vldb/2004}, Ee = {http://www.vldb.org/conf/2004/RS4P5.PDF}, Keywords = {XML XQuery algebra optimization tableaux NEXT}, Pages = {168-179}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/Deutsch.Papakonstantinou.ea_NEXT_VLDB_2004a.pdf}, Title = {{The NEXT Logical Framework for XQuery}}, Url = {http://www.vldb.org/conf/2004/RS4P5.PDF}, Year = {2004}, Abstract = {Classical logical optimization techniques rely on a logical semantics of the query language. The adaptation of these techniques to XQuery is precluded by its definition as a functional language with operational semantics. We introduce Nested XML Tableaux which enable a logical foundation for XQuery semantics and provide the logical plan optimization framework of our XQuery processor. As a proof of concept, we develop and evaluate a minimization algorithm for removing redundant navigation within and across nested subqueries. The rich XQuery features create key challenges that fundamentally extend the prior work on the problems of minimizing conjunctive and tree pattern queries.}} @inproceedings{Deutsch.Tannen_ContainmentXPath_KRDB_2001, Author = {Deutsch, Alin and Tannen, Val}, Booktitle = {Proc. Int. Workshop on Knowledge Representation meets Databases}, Conference-Abbr = {KRDB}, Keywords = {XML XPath query containment fragments query languages}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/Containment/Deutsch.Tannen_ContainmentXPath_KRDB_2001.pdf}, Title = {{Containment and Integrity Constraints for XPath Fragments}}, Url = {http://ceur-ws.org/Vol-45/01-deutsch.ps}, Year = {2001}, Abstract = {XPath is a W3C standard that plays a crucial role in several in uential query transformation and schema standards for XML Motivated by the larger challenge of XML query optimization we investigate the problem of containment of XPath expressions under integrity constraints that are in turn formulated with the help of XPath expressions Our core formalism consists of a fragment of XPath that we call simple and a corresponding class of of integrity constraints that we call simple XPath integrity constraints SXIC SXIC s can express many database style con straints including key and foreign key constraints speci ed in the XML Schema standard proposal as well as many constraints implied by DTDs We identify a subclass of bounded SXIC s under which containment of simple XPath expres sions is decidable but we show that even modest use of unbounded SXIC s makes the problem undecidable In particular the addition of unbounded constraints implied by DTDs leads to undecidability. We give tight P-bounds for the simple XPath containment problem and tight NP bounds for the disjunction free subfragment while even identifying a PTIME subcase We also show that decidability of containment under SXIC s still holds if the expressions contain certain additional features, e.g. wildcard although the complexity jumps to P even for the disjunction free subfragment. We know that our results can be extended to some but not all of the XPath features that depend on document order The decidability of containment of simple XPath expressions in the presence of DTDs only remains open although we can show that the problem is PSPACE hard as well as the problem for full edged XPath expressions even in the absence of integrity constraints.}} @inproceedings{Diao.Florescu.ea_MemoizationXQuery_XSym_2004, Author = {Diao, Yanlei and Florescu, Daniela and Kossmann, Donald and Carey, Michael J. and Franklin, Michael J.}, Booktitle = {Proc. Int. Database Symposium}, Conference-Abbr = {XSym}, Keywords = {XML XQuery memoization processor implementation}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/ProcessorsAndSystems/Diao.Florescu.ea_MemoizationXQuery_XSym_2004.pdf}, Title = {{Implementing Memoization in a Streaming XQuery Processor}}, Url = {http://www.cs.berkeley.edu/~franklin/Papers/MemoXSym.pdf}, Year = {2004}, Abstract = {In this paper, we describe an approach to boosting the performance of an XQuery engine by identifying and exploiting opportunities to share processing both within and across XML queries. We first explain where sharing opportunities arise in the world of XML query processing. We then describe an approach to shared XQuery processing based on memoization, providing details of an implementation that we built by extending the streaming XQuery processor that BEA Systems incorporates as part of their BEA WebLogic Integration 8.1 product. To explore the potential performance gains offered by our approach, we present results from an experimental study of its performance over a collection of use-case-inspired synthetic query workloads. The performance results show that significant overall gains are indeed available.}} @inproceedings{Dong.Bailey_StaticAnalysisXSLT_ADC_2004, Author = {Dong, Ce and Bailey, James}, Booktitle = {Proc. Australasian Database Conf.}, Conference-Abbr = {ADC}, Isbn = {1-111-11111-1}, Keywords = {XML XSLT error checking typing query languages}, Location = {Dunedin, New Zealand}, Pages = {151--160}, Pdf = {QueryEvaluation/XML/Containment/Dong.Bailey_StaticAnalysisXSLT_ADC_2004.pdf}, Publisher = {Australian Computer Society, Inc.}, Title = {{Static Analysis of XSLT Programs}}, Url = {http://www.cs.mu.oz.au/~jbailey/papers/adc.pdf}, Year = {2004}, Abstract = {XML is becoming the dominant standard for representing and exchanging data on the World Wide Web. The ability to transform and present data in XML is crucial and XSLT (Extensible Stylesheet Language Transformations) is the principal programming language that supports this activity. Methods for analysis of XSLT programs are currently an important open issue. In this paper, we discuss new methods for analysing XSLT programs, which return information about reachability, invalid calling relationships and termination properties. Our methods are based on the determination of the associations which can exist between components of an XSLT program, refined by the knowledge from a DTD. Such analysis is important for debugging and verification of XSLT programs and also their optimisation.}} @inproceedings{El-Sayed.Dimitrova.ea_EfficientOrder_WIDM_2003, Address = {New York, NY, USA}, Author = {El-Sayed, Maged and Dimitrova, Katica and Rundensteiner, Elke A.}, Booktitle = {Proc. Int. Workshop on Web Information and Data Management}, Conference-Abbr = {WIDM}, Doi = {http://doi.acm.org/10.1145/956699.956731}, Isbn = {1-58113-725-7}, Keywords = {XML query processing order optimization operators}, Location = {New Orleans, Louisiana, USA}, Pages = {147--154}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/OrderDuplicates/El-Sayed.Dimitrova.ea_EfficientOrder_WIDM_2003.pdf}, Publisher = {ACM Press}, Title = {{Efficiently Supporting Order in XML Query Processing}}, Url = {http://davis.wpi.edu/~dsrg/rainbow/publications/XMLorder_8-1-04.pdf}, Year = {2003}, Abstract = {Query processing over XML data sources has emerged as a popular topic. XML is an ordered data model and XQuery expressions return results that have a well-defined order. However little work on how order is supported in XML query processing has been done to date. In this paper we study the challenges related to handling order in the XML context, namely challenges imposed by the XML data model, by the variety of distinct XML operators and by incremental view maintenance. We have proposed an efficient solution that addresses these issues. We use a key encoding for XML nodes that supports both node identity and node order. We have designed order encoding rules based on the XML algebraic query execution data model and on node encodings that does not require any actual sorting for intermediate results during execution. Our approach supports more efficient incremental view maintenance as it makes most XML operators distributive with respect to bag union. Our approach is implemented in the context of Rainbow [25], an XML data management system developed at WPI. We prove the correctness of our order encoding approach, namely that it ensures order handling for query processing and for view maintenance. We also show, through experiments, that the overhead of maintaining order in our approach is indeed neglectible.}} @inproceedings{Fegaras.Levine.ea_QueryStreamedXML_CIKM_2002, Address = {New York, NY, USA}, Author = {Fegaras, Leonidas and Levine, David and Bose, Sujoe and Chaluvadi, Vamsi}, Booktitle = {Proc. Int. Conf. on Information and Knowledge Management}, Conference-Abbr = {CIKM}, Doi = {http://doi.acm.org/10.1145/584792.584816}, Isbn = {1-58113-492-4}, Keywords = {XML stream algebra query decorrelation non-blocking stream}, Location = {McLean, Virginia, USA}, Pages = {126--133}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/Fegaras.Levine.ea_QueryStreamedXML_CIKM_2002.pdf}, Publisher = {ACM Press}, Title = {{Query Processing of Streamed XML Data}}, Url = {http://lambda.uta.edu/cikm02.pdf}, Year = {2002}, Abstract = {We are addressing the efficient processing of continuous XML streams, in which the server broadcasts XML data to multiple clients concurrently through a multicast data stream, while each client is fully responsible for processing the stream. In our framework, a server may disseminate XML fragments from multiple documents in the same stream, can repeat or replace fragments, and can introduce new fragments or delete invalid ones. A client uses a light-weight database based on our proposed XML algebra to cache stream data and to evaluate XML queries against these data. The synchronization between clients and servers is achieved through annotations and punctuations transmitted along with the data streams. We are presenting a framework for processing XML queries in XQuery form over continuous XML streams. Our framework is based on a novel XML algebra and a new algebraic optimization framework based on query decorrelation, which is essential for non-blocking stream processing.}} @inproceedings{Fernandez.Simeon.ea_Galax_VLDB_2003, Author = {Fern{\'a}ndez, Mary and Sim{\'e}on, J{\'e}r{\^o}me and Choi, Byron and Marian, Am{\'e}lie and Sur, Gargi}, Booktitle = {Proc. Int. Conf. on Very Large Databases}, Conference-Abbr = {VLDB}, Keywords = {XML XQuery galax implementation query languages}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/ProcessorsAndSystems/Fernandez.Simeon.ea_Galax_VLDB_2003.pdf}, Title = {{Implementing XQuery 1.0 : The Galax Experience}}, Url = {http://www.vldb.org/conf/2003/papers/S35P07.pdf}, Year = {2003}, Abstract = {Galax is a light-weight, portable, open-source implementation of XQuery 1.0. Started in December 2000 as a small prototype designed to test the XQuery static type system, Galax has now become a solid implementation, aiming at full conformance with the family of XQuery 1.0 specifi- cations. Because of its completeness and open architecture, Galax also turns out to be a very convenient platform for researchers interested in experimenting with XQuery optimization. We demonstrate the Galax system as well as its most advanced features, including support for XPath 2.0, XML Schema and static typechecking. We also present some of our first experiments with optimization. Notably, we demonstrate query rewriting capabilities in the Galax compiler, and the ability to run queries on documents up to a Gigabyte without the need for preindexing. Although early versions of Galax have been shown in industrial conferences over the last two years, this is the first time it is demonstrated in the database community.}} @article{Fiebig.Moerkotte_AlgebraicXMLConstr_WWWJ_2001, Address = {Hingham, MA, USA}, Author = {Fiebig, Thorsten and Moerkotte, Guido}, Doi = {http://dx.doi.org/10.1023/A:1013831700817}, Issn = {1386-145X}, Journal = {World Wide Web}, Journal-Abbr = {WWWJ}, Keywords = {XML XQuery Natix construction algebraic}, Number = {3}, Pages = {167--187}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/Fiebig.Moerkotte_AlgebraicXMLConstr_WWWJ_2001.pdf}, Publisher = {Kluwer Academic Publishers}, Title = {{Algebraic XML Construction and its Optimization in Natix}}, Url = {http://portal.acm.org/citation.cfm?id=598761}, Volume = {4}, Year = {2001}, Abstract = {While using an algebra that acts on sets of variable bindings for evaluating XML queries, the problem of constructing XML from these bindings arises. One approach is to define a powerful operator that is able to perform a complex construction of a representation of the XML result document. The drawback is that such an operator in its generality is hard to implement and disables algebraic optimization since it has to be executed last in the plan. Therefore we suggest to construct XML documents by special query execution plans called construction plans built from simple, easy to implement and efficient operators. The paper proposes four simple algebraic operators needed for XML document construction. Further, we introduce an optimizing translation algorithm of construction clauses into algebraic expressions and briefly point out algebraic optimizations enabled by our approach.}} @article{Florescu.Hillery.ea_BEAXQuery_VLDBJ_2004, Author = {Florescu, Daniela and Hillery, Chris and Kossmann, Donald and Lucas, Paul and Riccardi, Fabio and Westmann, Till and Carey, Michael J. and Sundararajan, Arvind}, Doi = {http://dx.doi.org/10.1007/s00778-004-0137-1}, Issn = {1066-8888}, Journal = {VLDB Journal}, Journal-Abbr = {VLDBJ}, Keywords = {XML XQuery query processing implementation query languages}, Number = {3}, Pages = {294--315}, Pdf = {QueryEvaluation/XML/ProcessorsAndSystems/Florescu.Hillery.ea_BEAXQuery_VLDBJ_2004.pdf}, Publisher = {Springer-Verlag New York, Inc.}, Title = {{The BEA Streaming XQuery Processor}}, Url = {http://www-dbs.informatik.uni-heidelberg.de/publications/vldbj.pdf}, Volume = {13}, Year = {2004}, Abstract = {This paper describes the design, implementation, and performance characteristics of a commercial XQuery processing engine, the BEA streaming XQuery processor. This XQuery engine was designed to provide high performance for message-processing applications, i.e., for transforming XML data streams. The engine is a central component of the 8.1 release of BEA?s WebLogic Integration (WLI) product. The BEA XQuery engine is fully compliant with the August 2002 draft of the W3C XML Query Language specification and we are currently porting it to the latest version of the XQuery language (July 2004). A goal of this paper is to describe how a fully compliant yet efficient XQuery engine has been built from a few relatively simple components and well-understood technologies.}} @inproceedings{Fokoue.Rose.ea_XSLT2XQuery_WWW_2005, Address = {New York, NY, USA}, Author = {Fokoue, Achille and Rose, Kristoffer and Simeon, Jerome and Villard, Lionel}, Booktitle = {Proc. Int. World Wide Web Conf.}, Conference-Abbr = {WWW}, Doi = {http://doi.acm.org/10.1145/1060745.1060844}, Isbn = {1-59593-046-9}, Keywords = {XML XSLT XQuery translation compilation expressiveness}, Location = {Chiba, Japan}, Pages = {682--691}, Pdf = {QueryEvaluation/XML/ProcessorsAndSystems/Translating/Fokoue.Rose.ea_XSLT2XQuery_WWW_2005.pdf}, Publisher = {ACM Press}, Title = {Compiling XSLT 2.0 into XQuery 1.0}, Url = {http://portal.acm.org/citation.cfm?id=1060745.1060844}, Year = {2005}, Abstract = {As XQuery is gathering momentum as the standard query language for XML, there is a growing interest in using it as an integral part of the XML application development infrastructure. In that context, one question which is often raised is how well XQuery interoperates with other XML languages, and notably with XSLT. XQuery 1.0 [16] and XSLT 2.0 [7] share a lot in common: they share XPath 2.0 as a common sub-language and have the same expressiveness. However, they are based on fairly different programming paradigms. While XSLT has adopted a highly declarative template based approach, XQuery relies on a simpler, and more operational, functional approach.In this paper, we present an approach to compile XSLT 2.0 into XQuery 1.0, and a working implementation of that approach. The compilation rules explain how XSLT's template-based approach can be implemented using the functional approach of XQuery and underpins the tight connection between the two languages. The resulting compiler can be used to migrate a XSLT code base to XQuery, or to enable the use of XQuery runtimes (e.g., as will soon be provided by most relational database management systems) for XSLT users. We also identify a number of areas where compatibility between the two languages could be improved. Finally, we show experiments on actual XSLT stylesheets, demonstrating the applicability of the approach in practice.}} @inproceedings{Frasincar.Houben.ea_XALAlgebra_CRPITS_2002, Address = {Darlinghurst, Australia, Australia}, Author = {Frasincar, Flavius and Houben, Geert-Jan and Pau, Cristian}, Booktitle = {Proc. Australasian Conf. on Database Technologies}, Conference-Abbr = {CRPITS}, Isbn = {0-909925-83-6}, Keywords = {XML XQuery XAL XML algebra optimization}, Location = {Melbourne, Victoria, Australia}, Pages = {49--56}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/Frasincar.Houben.ea_XALAlgebra_CRPITS_2002.pdf}, Publisher = {Australian Computer Society, Inc.}, Title = {{XAL: an Algebra for XML Query Optimization}}, Url = {http://portal.acm.org/citation.cfm?id=563906.563912}, Year = {2002}, Abstract = {This paper proposes XAL, an XML ALgebra. Its novelty is based on the simplicity of its data model and its well-defined logical operators, which makes it suitable for composability, optimizability, and semantics definition of a query language for XML data. At the heart of the algebra resides the notion of collection, a concept similar to the mathematician's monad or functional programmer's comprehension. The operators are classified in three clusters: extraction operators retrieve the needed information from XML documents, meta-operators control the evaluation of expressions, and construction operators build new XML documents from the extracted data. The resulting algebra has optimization laws similar to the known laws for transforming relational queries. As a consequence, we propose a heuristic optimization algorithm similar to its relational algebra counterpart.}} @techreport{Galanis.Viglas.ea_FollowingPathsof_TR_2002, Author = {Galanis, Leonidas and Viglas, Efstratios and Dewitt, David J. and Naughton, Jeffrey. F. and Maier, David}, Institution = {University of Wisconsin}, Keywords = {XML Quilt algebra xml query optimization niagara}, Number = {363}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/Galanis.Viglas.ea_FollowingPathsof_TR_2002.pdf}, Title = {{Following the Paths of XML Data: An Algebraic Framework for XML Query Evaluation}}, Url = {http://www.csd.uch.gr/~hy561/Papers/algebraicXMLframework01.pdf}, Year = {2002}, Abstract = {This paper introduces an algebraic framework for expressing and evaluating queries over XML data. It presents the underlying assumptions of the framework, describes the input and output of the algebraic operators, and de nes these operators and their semantics. It evaluates the framework with regard to other proposed XML query algebras. Examples show that this framework is flexible enough to capture queries expressed in Quilt, one of the dominant XML query languages. We have used this algebra in the context of an Internet query engine, in which it is used to formulate logical plans for XML-QL queries. We define equivalence rules that provide opportunities for optimization, and give example cases that point out the usefulness of these rules.}} @inproceedings{Gottlob.Koch_MonadicDatalWeb_JACM_2004, Author = {Gottlob, Georg and Koch, Christoph}, Booktitle = {Journal of the ACM}, Conference-Abbr = {JACM}, Editor = {51}, Keywords = {XML query languages web extraction datalog complexity}, Owner = {Tim Furche}, Pages = {74--113}, Pdf = {QueryEvaluation/XML/Comlexity/Gottlob.Koch_MonadicDatalWeb_JACM_2004.pdf}, Title = {{Monadic Datalog and the Expressive Power of Languages for Web Information Extraction}}, Url = {http://www-db.cs.uni-sb.de/~koch/download/0211020.pdf}, Volume = {1}, Year = {2004}, Abstract = {Research on information extraction from Web pages (wrapping) has seen much activity recently (particularly systems implementations), but little work has been done on formally studying the expressiveness of the formalisms proposed or on the theoretical foundations of wrapping. In this paper, we first study monadic datalog over trees as a wrapping language. We show that this simple language is equivalent to monadic second order logic (MSO) in its ability to specify wrappers. We believe that MSO has the right expressiveness required for Web information extraction and propose MSO as a yardstick for evaluating and comparing wrappers. Along the way, several other results on the complexity of query evaluation and query containment for monadic datalog over trees are established, and a simple normal form for this language is presented. Using the above results, we subsequently study the kernel fragment Elog? of the Elog wrapping language used in the Lixto system (a visual wrapper generator). Curiously, Elog? exactly captures MSO, yet is easier to use. Indeed, programs in this language can be entirely visually specified.}} @article{Gottlob.Koch.ea_ComplexityXPath_JACM_2005, Author = {Gottlob, Georg and Koch, Christoph and Pichler, Reinhard and Segoufin, Luc}, Date-Modified = {2006-02-01 17:38:21 +0100}, Group = {Matrix Method}, Journal = {Journal of the ACM}, Journal-Abbr = {JACM}, Keywords = {XML XPath complexity querying typing}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/Comlexity/Gottlob.Koch.ea_ComplexityXPath_JACM_2005.pdf}, Title = {{The Complexity of XPath Query Evaluation and XML Typing}}, Url = {http://www-db.cs.uni-sb.de/~koch/download/jacm2.pdf}, Year = {2005}, Abstract = {We study the complexity of two central XML processing problems. The rst is XPath 1.0 query processing, which has been shown to be in PTime in previous work. We prove that both the data complexity and the query complexity of XPath 1.0 fall into lower (highly parallelizable) complexity classes, while the combined complexity is PTime-hard. Subsequently, we study the sources of this hardness and identify a large and practically important fragment of XPath 1.0 for which the combined complexity is LogCFL-complete and, therefore, in the highly parallelizable complexity class NC2. The second problem is the complexity of validating XML documents against various typing schemes like Document Type De nitions (DTDs), XML Schema De nitions (XSDs), and tree automata, both with respect to data and to combined complexity. For data complexity, we prove that validation is in LogSpace and depends crucially on how XML data is represented. For the combined complexity, we show that the complexity ranges from LogSpace to LogCFL, depending on the typing scheme.}} @inproceedings{Gottlob.Koch.ea_ConjunctiveQsTrees_PODS_2004, Author = {Gottlob, Georg and Koch, Christoph and Schulz, Klaus}, Booktitle = {Proc. Symposium on Principles of Database Systems}, Conference-Abbr = {PODS}, Keywords = {Query Evaluation XML XPath Conjunctive Query Complexity REWERSE}, Month = {6}, Note = {I4}, Owner = {Tim Furche}, Pages = {189--200}, Pdf = {QueryEvaluation/XML/Comlexity/Gottlob.Koch.ea_ConjunctiveQsTrees_PODS_2004.pdf}, Title = {{Conjunctive Queries over Trees}}, Url = {http://www.acm.org/sigmod/pods/proc04/pdf/P-19.pdf}, Urldate = {2005/01/28}, Year = {2004}, Abstract = {We study the complexity and expressive power of conjunctive queries over unranked labeled trees, where the tree structures are represented using ?axis relations? such as ?child?, ?descendant?, and ?following? (we consider a superset of the XPath axes) as well as unary relations for node labels. (Cyclic) conjunctive queries over trees occur in a wide range of data management scenarios related to XML, the Web, and computational linguistics. We establish a framework for characterizing structures representing trees for which conjunctive queries can be evaluated efficiently. Then we completely chart the tractability frontier of the problem for our axis relations, i.e., we nd all subsetmaximal sets of axes for which query evaluation is in polynomial time. All polynomial-time results are obtained immediately using the proof techniques from our framework. Finally, we study the expressiveness of conjunctive queries over trees and compare it to the expressive power of fragments of XPath. We show that for each conjunctive query, there is an equivalent acyclic positive query (i.e., a set of acyclic conjunctive queries), but that in general this query is not of polynomial size.}} @inproceedings{Grinev.Lizorkin_FunctionInlXQ_ADBIS_2004, Author = {Grinev, Maxim and Lizorkin, Dmitry}, Bibsource = {DBLP, http://dblp.uni-trier.de}, Booktitle = {East-European Conf. on Advances in Databases and Information Systems}, Conference-Abbr = {ADBIS}, Ee = {http://www.sztaki.hu/conferences/ADBIS/4-Lizorkin.pdf}, Keywords = {XML XQuery function inlining optimization rewriting}, Pdf = {QueryEvaluation/XML/Compilation/Grinev.Lizorkin_FunctionInlXQ_ADBIS_2004.pdf}, Title = {{XQuery Function Inlining for Optimizing XQuery Queries}}, Url = {http://www.sztaki.hu/conferences/ADBIS/4-Lizorkin.pdf}, Year = {2004}} @inproceedings{Grinev.Pleshachkov_RewrTransf_IDEAS_2005, Author = {Grinev, Maxim and Pleshachkov, Peter}, Booktitle = {Proc. Int. Database Engineering and Application Symposium}, Conference-Abbr = {IDEAS}, Keywords = {XML XQuery rewriting transformation query}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/Containment/Grinev.Pleshachkov_RewrTransf_IDEAS_2005.pdf}, Title = {{Rewriting-based Optimization for XQuery Transformational Queries}}, Url = {http://www.ispras.ru/~grinev/mypapers/rewrite-transformation-ext.pdf}, Year = {2005}, Abstract = {The modern XML query language called XQuery includes advanced facilities both to query and to transform XML data. An XQuery query optimizer should be able to optimize any query. For ?querying? queries almost all techniques inherited from SQLoriented DBMS may be applied. The XQuery transformation facilities are XML-specific and have no counterparts in other query languages. That is why XQuery transformational queries need to be optimized with novel techniques. In this paper two kinds of such techniques (namely push predicates down XML element constructors and projection of transformation) are considered. A subset of XQuery for which these techniques can be fully implemented is identified. This subset seems to be the most intersting from the practical viewpoint. Rewriting rules for this subset are proposed and the correctness of these rules is formally justified. For the rest of the language we propose solutions that works for the most of common cases or consider the problems we have encountered.}} @inproceedings{Grohe.Koch.ea_LowerBoundsMem_ICALP_2005, Author = {Grohe, Martin and Koch, Christoph and Schweikardt, Nicole}, Booktitle = {Proc. Int. Colloquium on Automata, Languages, and Programming}, Conference-Abbr = {ICALP}, Keywords = {XML lower bounds memory streaming XPath}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/Comlexity/Grohe.Koch.ea_LowerBoundsMem_ICALP_2005.pdf}, Title = {{Tight Lower Bounds for Query Processing on Streaming and External Memory Data}}, Url = {http://www.infosys.uni-sb.de/~koch/download/icalp05B075.pdf}, Year = {2005}, Abstract = {We study a clean machine model for external memory and stream processing. We show that the number of scans of the external data induces a strict hierarchy (as long as work space is su ciently small, e.g., polylogarithmic in the size of the input). We also show that neither joins nor sorting are feasible if the product of the number r(n) of scans of the external memory and the size s(n) of the internal memory bu ers is su ciently small, e.g., of size o(p5 n). We also establish tight bounds for the complexity of XPath evaluation and ltering.}} @inproceedings{Grust_AcceleratingXPath_SIGMOD_2002, Author = {Grust, Thorsten}, Booktitle = {Proc. ACM SIGMOD Int. Conf. on Management of Data}, Conference-Abbr = {SIGMOD}, Keywords = {XML XPath relational implementation location steps efficiency accelerating}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/IndexingLabelling/Grust_AcceleratingXPath_SIGMOD_2002.pdf}, Title = {{Accelerating XPath Location Steps}}, Url = {http://www.in.tu-clausthal.de/~grust/files/xpath-accel.pdf}, Year = {2002}, Abstract = {This work is a proposal for a database index structure that has been speci cally designed to support the evaluation of XPath queries. As such, the index is capable to support all XPath axes (including ancestor, following, precedingsibling, descendant-or-self, etc.). This feature lets the index stand out among related work on XML indexing structures which had a focus on regular path expressions (which correspond to the XPath axes children and descendantor- self plus name tests). Its ability to start traversals from arbitrary context nodes in an XML document additionally enables the index to support the evaluation of path traversals embedded in XQuery expressions. Despite its exibility, the new index can be implemented and queried using purely relational techniques, but it performs especially well if the underlying database host provides support for R-trees. A performance assessment which shows quite promising results completes this proposal.}} @article{Grust.Keulen.ea_AcceleratingXPath_TODS_2004, Author = {Grust, Torsten and Keulen, Maurice Van and Teubner, Jens}, Doi = {http://doi.acm.org/10.1145/974750.974754}, Issn = {0362-5915}, Journal = {ACM Transactions on Database Systems}, Journal-Abbr = {TODS}, Keywords = {XML XPath location steps relational implementation encoding}, Number = {1}, Pages = {91--131}, Pdf = {QueryEvaluation/XML/ProcessorsAndSystems/Translating/Grust.Keulen.ea_AcceleratingXPath_TODS_2004.pdf}, Publisher = {ACM Press}, Title = {{Accelerating XPath Evaluation in any RDBMS}}, Url = {http://portal.acm.org/citation.cfm?id=974754}, Volume = {29}, Year = {2004}, Abstract = {This article is a proposal for a database index structure, the XPath accelerator, that has been specifically designed to support the evaluation of XPath path expressions. As such, the index is capable to support all XPath axes (including ancestor, following, preceding-sibling, descendant-or-self, etc.). This feature lets the index stand out among related work on XML indexing structures which had a focus on the child and descendant axes only. The index has been designed with a close eye on the XPath semantics as well as the desire to engineer its internals so that it can be supported well by existing relational database query processing technology: the index (a) permits set-oriented (or, rather, sequence-oriented) path evaluation, and (b) can be implemented and queried using well-established relational index structures, notably B-trees and R-trees.We discuss the implementation of the XPath accelerator on top of different database backends and show that the index performs well on all levels of the memory hierarchy, including disk-based and main-memory based database systems.}} @inproceedings{Grust.Keulen.ea_StaircaseJoin_VLDB_2003, Author = {Grust, Torsten and van Keulen, Maurice and Teubner, Jens}, Booktitle = {Proc. Int. Conf. on Very Large Databases}, Conference-Abbr = {VLDB}, Keywords = {XML staircase join structural join relational}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/StructuralJoins/Grust.Keulen.ea_StaircaseJoin_VLDB_2003.pdf}, Title = {{Staircase Join: Teach A Relational DBMS to Watch its (Axis) Steps}}, Url = {http://www.inf.uni-konstanz.de/~teubner/publications/watch-axis-steps.pdf}, Year = {2003}, Abstract = {Relational query processors derive much of their e ectiveness from the awareness of speci c table properties like sort order, size, or absence of duplicate tuples. This text applies (and adapts) this successful principle to database-supported XML and XPath processing: the relational system is made tree aware, i.e., tree properties like subtree size, intersection of paths, inclusion or disjointness of subtrees are made explicit. We propose a local change to the database kernel, the staircase join, which encapsulates the necessary tree knowledge needed to improve XPath performance. Staircase join operates on an XML encoding which makes this knowledge available at the cost of simple integer operations. We finally report on quite promising experiments with a staircase join enhanced main-memory database kernel.}} @inproceedings{Grust.Sakr.ea_XQueryOnSQL_VLDB_2004, Author = {Grust, Torsten and Sakr, Sherif and Teubner, Jens}, Booktitle = {Proc. Int. Conf. on Very Large Databases}, Conference-Abbr = {VLDB}, Keywords = {XML XQuery relational implementation SQL}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/ProcessorsAndSystems/Translating/Grust.Sakr.ea_XQueryOnSQL_VLDB_2004.pdf}, Title = {{XQuery on SQL Hosts}}, Url = {http://www.in.tu-clausthal.de/~grust/files/sql-mapping.pdf}, Year = {2004}, Abstract = {Relational database systems may be turned into efficient XML and XPath processors if the system is provided with a suitable relational tree encoding. This paper extends this relational XML processing stack and shows that an RDBMS can also serve as a highly efficient XQuery runtime environment. Our approach is purely relational: XQuery expressions are compiled into SQL code which operates on the tree encoding. The core of the compilation procedure trades XQuery's notions of variable scopes and nested iteration (FLWOR blocks) for equi-joins. The resulting relational XQuery processor closely adheres to the language semantics, e.g., it obeys node identity as well as document and sequence order, and can support XQuery's full axis feature. The system exhibits quite promising performance figures in experiments. Somewhat unexpectedly, we will also see that the XQuery compiler can make good use of SQL's OLAP functionality.}} @inproceedings{Grust.Teubner_RAXQuery_TDM_2004, Author = {Grust, Torsten and Teubner, Jens}, Booktitle = {Proc. Twente Data Management Workshop on XML Databases and Information Retrieval}, Conference-Abbr = {TDM}, Date-Modified = {2006-02-01 17:29:59 +0100}, Keywords = {XML XQuery relational algebra SQL translation}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/ProcessorsAndSystems/Translating/Grust.Teubner_RAXQuery_TDM_2004.pdf}, Title = {{Relational Algebra: Mother Tongue - XQuery: Fluent}}, Url = {http://www.in.tu-clausthal.de/~grust/files/algebra-mapping.pdf}, Year = {2004}, Abstract = {This work may be seen as a further proof of the versatility of the relational database model. Here, we add XQuery to the catalog of languages which RDBMSs are able to "speak" fluently. Given suitable relational encodings of sequences and ordered, unranked trees the two data structures that form the backbone of the XML and XQuery data models we describe a compiler that translates XQuery expressions into a simple and quite standard relational algebra which we expect to be efficiently implementable on top of any relational query engine. The compilation procedure is fully compositional and emits algebraic code that strictly adheres to the XQuery language semantics: document and sequence order as well as node identity are obeyed. We exercise special care in translating arbitrarily nested XQuery FLWOR iteration constructs into equi-joins, an operation which RDBMSs can perform particularly fast. The resulting purely relational XQuery processor shows promising performance figures in experiments.}} @inproceedings{Guo.Li.ea_ScalableXSLT_APWEB_2004, Author = {Guo, Zhimao and Li, Min and Wang, Xiaoling and Zhou, Aoying}, Booktitle = {Proc. Asia Pacific Web Conference}, Conference-Abbr = {APWEB}, Keywords = {XML XSLT evaluation optimization query languages}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/ProcessorsAndSystems/Streaming/Guo.Li.ea_ScalableXSLT_APWEB_2004.pdf}, Title = {{Scalable XSLT Evaluation}}, Url = {http://arxiv.org/abs/cs.DB/0408051}, Year = {2004}, Abstract = {XSLT is an increasingly popular language for processing XML data. It is widely supported by application platform software. However, little optimization effort has been made inside the current XSLT processing engines. Evaluating a very simple XSLT program on a large XML document with a simple schema may result in extensive usage of memory. In this paper, we present a novel notion of Streaming Processing Model (SPM) to evaluate a subset of XSLT programs on XML documents, especially large ones. With SPM, an XSLT processor can transform an XML source document to other formats without extra memory buffers required. Therefore, our approach can not only tackle large source documents, but also produce large results. We demonstrate with a performance study the advantages of the SPM approach. Experimental results clearly confirm that SPM improves XSLT evaluation typically 2 to 10 times better than the existing approaches. Moreover, the SPM approach also features high scalability.}} @article{Hamilton.Selinger_ConversationwithPat_ACMQ_2005, Author = {Hamilton, James and Selinger, Pat}, Journal = {ACM Queue}, Journal-Abbr = {ACMQ}, Keywords = {database vision metadata unstructured information}, Month = {April}, Number = {3}, Owner = {Tim Furche}, Title = {{A Conversation with Pat Selinger}}, Url = {http://www.acmqueue.org/modules.php?name=Content&pa=showpage&pid=297&page=1}, Volume = {3}, Year = {2005}, Abstract = {Take Pat Selinger of IBM and James Hamilton of Microsoft and put them in a conversation together, and you may hear everything you wanted to know about database technology and weren?t afraid to ask.}} @inproceedings{Helmer.Kanne.ea_ParamTranslXPath_WISE_2002, Address = {Washington, DC, USA}, Author = {Helmer, Sven and Kanne, Carl-Christian and Moerkotte, Guido}, Booktitle = {Proc. Int. Conf. on Web Information Systems Engineering}, Conference-Abbr = {WISE}, Isbn = {0-7695-1766-8}, Keywords = {XML XPath algebra Natix translation navgiation}, Pages = {215--224}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/Helmer.Kanne.ea_ParamTranslXPath_WISE_2002.pdf}, Publisher = {IEEE Computer Society}, Title = {{Optimized Translation of XPath into Algebraic Expressions Parameterized by Programs Containing Navigational Primitives}}, Url = {http://www.csd.uch.gr/~hy561/Papers/XPath-Natix-wise02.pdf}, Year = {2002}, Abstract = {We propose a new approach for the efficient evaluationof XPath expressions. This is important, since XPath is notonly used as a simple, stand-alone query language, but isalso an essential ingredient of XQuery and XSLT.The main idea of our approach is to translate XPath intoalgebraic expressions parameterized with programs. Theseprograms are mainly built from navigational primitives likeaccessing the first child or the next sibling. The goals ofthe approach are 1) to enable pipelined evaluation, 2) toavoid producing duplicate (intermediate) result nodes, 3) tovisit as few document nodes as possible, and 4) to avoidvisiting nodes more than once. This improves the existingapproaches, because our method is highly efficient.}} @inproceedings{Helmer.May.ea_QueryDecorrel_XSym_2003, Author = {Helmer, Sven and May, Norman and Moerkotte, Guido}, Booktitle = {Proc. Int. XML Database Symposium}, Conference-Abbr = {XSym}, Keywords = {XQuery nested queries query decorrelation}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/NestedQueries/Helmer.May.ea_QueryDecorrel_XSym_2003.pdf}, Title = {{Three Cases for Query Decorrelation in XQuery}}, Url = {http://pi3.informatik.uni-mannheim.de/~norman/unnesting_xmlsym03.pdf}, Year = {2003}, Abstract = {We present algebraic equivalences that allow to unnest nested algebraic expressions for order-preserving algebraic operators. We illustrate how these equivalences can be applied successfully to unnest nested queries given in the XQuery language. Measurements illustrate the performance gains possible by unnesting.}} @inproceedings{Hidders_SatisfiabilityXPath_DBPL_2003, Author = {Hidders, Jan}, Booktitle = {Int. Workshop on Databse Programming Languages}, Conference-Abbr = {DBPL}, Keywords = {XML XPath satisfiability query languages theory}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/Containment/Hidders_SatisfiabilityXPath_DBPL_2003.pdf}, Title = {{Satisfiability of XPath Expressions}}, Url = {http://plantijn.ruca.ua.ac.be/~adrem/biborb/bibs/ADReM/papers/hidders03xpathsat.pdf}, Year = {2003}, Abstract = {In this paper, we investigate the complexity of deciding the satisfiability of XPath 2.0 expressions, i.e., whether there is an XML document for which their result is nonempty. Several fragments that allow certain types of expressions are classified as either in PTIME or NP-hard to see which type of expression make this a hard problem. Finally, we establish a link between XPath expressions and partial tree descriptions which are studied in computational linguistics.}} @inproceedings{Hung.Deng.ea_TOSS-TAX_SIGMOD_2004, Address = {New York, NY, USA}, Author = {Hung, Edward and Deng, Yu and Subrahmanian, V. S.}, Booktitle = {Proc. ACM SIGMOD Int. Conf. on Management of data}, Conference-Abbr = {SIGMOD}, Doi = {http://doi.acm.org/10.1145/1007568.1007649}, Isbn = {1-58113-859-8}, Keywords = {XML query TAX algebra optimization ontologies similarity queries}, Location = {Paris, France}, Pages = {719--730}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/Hung.Deng.ea_TOSS-TAX_SIGMOD_2004.pdf}, Publisher = {ACM Press}, Title = {{TOSS: An Extension of TAX with Ontologies and Similarity Queries}}, Url = {http://portal.acm.org/citation.cfm?id=1007649}, Year = {2004}, Abstract = {TAX is perhaps the best known extension of the relational algebra to handle queries to XML databases. One problem with TAX (as with many existing relational DBMSs) is that the semantics of terms in a TAX DB are not taken into account when answering queries. Thus, even though TAX answers queries with 100% precision, the recall of TAX is relatively low. Our TOSS system improves the recall of TAX via the concept of a similarity enhanced ontology (SEO). Intuitively, an ontology is a set of graphs describing relationships (such as isa, partof, etc.) between terms in a DB. An SEO also evaluates how similarities between terms (e.g. "J. Ullman", "Jeff Ullman", and "Jeffrey Ullman") affect ontologies. Finally, we show how the algebra proposed in TAX can be extended to take SEOs into account. The result is a system that provides a much higher answer quality than TAX does alone (quality is defined as the square root of the product of precision and recall). We experimentally evaluate the TOSS system on the DBLP and SIGMOD bibliographic databases and show that TOSS has acceptable performance.}} @inproceedings{Iacob.Dekhtyar_TowardsQueryLanguage_WebDB_2005, Author = {Iacob, Ionut and Dekhtyar, Alex}, Booktitle = {Proc. Int. Workshop on the Web and Databases}, Conference-Abbr = {WebDB}, Keywords = {XML XPath multi-hiearchy document-oriented information retrieval text ranges GODDAG}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/LanguageConstructs/XPath/Iacob.Dekhtyar_TowardsQueryLanguage_WebDB_2005.pdf}, Title = {{Towards a Query Language for Multihierarchical XML: Revisiting XPath}}, Url = {http://dblab.csr.uky.edu/~eiaco0/publications/webdb05.pdf}, Year = {2005}, Abstract = {In recent years it has been argued that when XML encodings become complex, DOM trees are no longer adequate for query processing. Alternative representations of XML documents, such as multi-colored trees have been proposed as a replacement for DOM trees for complex markup. In this paper we consider the use of Generalized Ordered-Descendant Directed Acyclic Graphs (GODDAGs) for the purpose of storing and querying complex document- centric XML. GODDAGs are designed to store multihierarchical XML markup over the shared PCDATA content. They support representation of overlapping markup, which otherwise cannot be represented easily in DOM. We describe how the semantics of XPath axes can be modified to define path expressions over GODDAG, and enhance it with the facilities to traverse and query overlapping markup. We provide efficient algorithms for axis evaluation over GODDAG and describe the implementation of the query processor based on our definitions and algorithms.}} @article{Jagadish.Al-Khalifa.ea_TIMBER_VLDBJ_2002, Address = {Secaucus, NJ, USA}, Author = {Jagadish, H. V. and Al-Khalifa, S. and Chapman, A. and Lakshmanan, L. V. S. and Nierman, A. and Paparizos, S. and Patel, J. M. and Srivastava, D. and Wiwatwattana, N. and Wu, Y. and Yu, C.}, Doi = {http://dx.doi.org/10.1007/s00778-002-0081-x}, Issn = {1066-8888}, Journal = {VLDB Journal}, Journal-Abbr = {VLDBJ}, Keywords = {XML XQuery TIMBER native database XML TAX algebra}, Number = {4}, Pages = {274--291}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/Jagadish.Al-Khalifa.ea_TIMBER_VLDBJ_2002.pdf}, Publisher = {Springer-Verlag New York, Inc.}, Title = {{TIMBER: A native XML Database}}, Url = {http://www.eecs.umich.edu/db/timber/files/timber.pdf}, Volume = {11}, Year = {2002}, Abstract = {This paper describes the overall design and architecture of the Timber XML database system currently being implemented at the University of Michigan. The system is based upon a bulk algebra for manipulating trees, and natively stores XML. New access methods have been developed to evaluate queries in the XML context, and new cost estimation and query optimization techniques have also been developed. We present performance numbers to support some of our design decisions. We believe that the key intellectual contribution of this system is a comprehensive set-at-a-time query processing ability in a native XML store, with all the standard components of relational query processing, including algebraic rewriting and a cost-based optimizer.}} @inproceedings{Jagadish.Lakshmanan.ea_ColorfulXML_SIGMOD_2004, Address = {New York, NY, USA}, Author = {Jagadish, H. V. and Lakshmanan, Laks V. S. and Scannapieco, Monica and Srivastava, Divesh and Wiwatwattana, Nuwee}, Booktitle = {Proc. ACM SIGMOD Int. Conf. on Management of Data}, Conference-Abbr = {SIGMOD}, Doi = {http://doi.acm.org/10.1145/1007568.1007598}, Isbn = {1-58113-859-8}, Keywords = {XML XQuery multiple hiearchies colored trees graph data model}, Location = {Paris, France}, Pages = {251--262}, Pdf = {QueryEvaluation/XML/LanguageConstructs/XQuery/Jagadish.Lakshmanan.ea_ColorfulXML_SIGMOD_2004.pdf}, Publisher = {ACM Press}, Title = {{Colorful XML: One Hierarchy isn't enough}}, Url = {http://www.research.att.com/~divesh/papers/jlssw2004-mct.pdf}, Year = {2004}, Abstract = {XML has a tree-structured data model, which is used to uniformly represent structured as well as semi-structured data, and also enable concise query specification in XQuery, via the use of its XPath (twig) patterns. This in turn can leverage the recently developed technology of structural join algorithms to evaluate the query efficiently. In this paper, we identify a fundamental tension in XML data modeling: (i) data represented as deep trees (which can make effective use of twig patterns) are often un-normalized, leading to update anomalies, while (ii) normalized data tends to be shallow, resulting in heavy use of expensive value-based joins in queries.Our solution to this data modeling problem is a novel multi-colored trees (MCT) logical data model, which is an evolutionary extension of the XML data model, and permits trees with multi-colored nodes to signify their participation in multiple hierarchies. This adds significant semantic structure to individual data nodes. We extend XQuery expressions to navigate between structurally related nodes, taking color into account, and also to create new colored trees as restructurings of an MCT database. While MCT serves as a significant evolutionary extension to XML as a logical data model, one of the key roles of XML is for information exchange. To enable exchange of MCT information, we develop algorithms for optimally serializing an MCT database as XML. We discuss alternative physical representations for MCT databases, using relational and native XML databases, and describe an implementation on top of the Timber native XML database. Experimental evaluation, using our prototype implementation, shows that not only are MCT queries/updates more succinct and easier to express than equivalent shallow tree XML queries, but they can also be significantly more efficient to evaluate than equivalent deep and shallow tree XML queries/updates.}} @inproceedings{Jagadish.Lakshmanan.ea_TAX_DBPL_2001, Author = {Jagadish, H. V. and Lakshmanan, Laks V. S. and Srivastava, Divesh and Thompson, Keith}, Booktitle = {Proc. Int. Workshop on Database Programming Languages}, Conference-Abbr = {DBPL}, Keywords = {XML TAX algebra TIMBER optimization}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/Jagadish.Lakshmanan.ea_TAX_DBPL_2001.pdf}, Title = {{TAX: A Tree Algebra for XML}}, Url = {http://www.cs.ubc.ca/~laks/tax-dbpl01-cr.pdf}, Year = {2001}, Abstract = {Querying XML has been the subject of much recent investigation. A formal bulk algebra is essential for applying database-style optimization to XML queries. We develop such an algebra, called TAX (Tree Algebra for XML), for manipulating XML data, modeled as forests of labeled ordered trees. Motivated both by aesthetic considerations of intuitiveness, and by efficient computability and amenability to optimization, we develop TAX as a natural extension of relational algebra, with a small set of operators. TAX is complete for relationl algebra extended with aggregation, and can express most queries expressible in popular XML query langauges. It forms the basis for the TIMBER XML database system currently under development by us.}} @inproceedings{Jain.Mahajan.ea_TranslatXSLT2SQL_WWW_2002, Author = {Jain, Sushant and Mahajan, Ratul and Suciu, Dan}, Booktitle = {Proc. Int. World Wide Web Conf.}, Conference-Abbr = {WWW}, Doi = {http://doi.acm.org/10.1145/511446.511526}, Isbn = {1-58113-449-5}, Keywords = {XML XSTL query processing relational implementation SQL}, Location = {Honolulu, Hawaii, USA}, Pages = {616--626}, Pdf = {QueryEvaluation/XML/ProcessorsAndSystems/Translating/Jain.Mahajan.ea_TranslatXSLT2SQL_WWW_2002.pdf}, Publisher = {ACM Press}, Title = {{Translating XSLT Programs to Efficient SQL Queries}}, Url = {http://www2002.org/CDROM/refereed/226/}, Year = {2002}, Abstract = {We present an algorithm for translating XSLT programs into SQL. Our context is that of virtual XML publishing, in which a single XML view is defined from a relational database, and subsequently queried with XSLT programs. Each XSLT program is translated into a single SQL query and run entirely in the database engine. Our translation works for a large fragment of XSLT, which we define, that includes descendant/ancestor axis, recursive templates, modes, parameters, and aggregates. We put considerable effort in generating correct and efficient SQL queries and describe several optimization techniques to achieve this efficiency. We have tested our system on all 22 SQL queries of the TPC-H database benchmark which we represented in XSLT and then translated back to SQL using our translator.}} @inproceedings{Kaushik.Bohannon.ea_FBIndex_SIGMOD_2002, Address = {New York, NY, USA}, Author = {Kaushik, Raghav and Bohannon, Philip and Naughton, Jeffrey F and Korth, Henry F}, Booktitle = {Proc. ACM SIGMOD Int. Conf. on Management of Data}, Conference-Abbr = {SIGMOD}, Doi = {http://doi.acm.org/10.1145/564691.564707}, Isbn = {1-58113-497-5}, Keywords = {XML XPath XQuery index forward-backward branching tree}, Location = {Madison, Wisconsin}, Pages = {133--144}, Pdf = {QueryEvaluation/XML/IndexingLabelling/Kaushik.Bohannon.ea_FBIndex_SIGMOD_2002.pdf}, Publisher = {ACM Press}, Title = {{Covering indexes for Branching Path Queries}}, Url = {http://portal.acm.org/citation.cfm?id=564691.564707}, Year = {2002}, Abstract = {In this paper, we ask if the traditional relational query acceleration techniques of summary tables and covering indexes have analogs for branching path expression queries over tree- or graph-structured XML data. Our answer is yes --- the forward-and-backward index already proposed in the literature can be viewed as a structure analogous to a summary table or covering index. We also show that it is the smallest such index that covers all branching path expression queries. While this index is very general, our experiments show that it can be so large in practice as to offer little performance improvement over evaluating queries directly on the data. Likening the forward-and-backward index to a covering index on all the attributes of several tables, we devise an index definition scheme to restrict the class of branching path expressions being indexed. The resulting index structures are dramatically smaller and perform better than the full forward-and-backward index for these classes of branching path expressions. This is roughly analogous to the situation in multidimensional or OLAP workloads, in which more highly aggregated summary tables can service a smaller subset of queries but can do so at increased performance. We evaluate the performance of our indexes on both relational decompositions of XML and a native storage technique. As expected, the performance benefit of an index is maximized when the query matches the index definition.}} @inproceedings{Koch.Scherzinger.ea_FluXQueryT_VLDB_2004, Author = {Koch, Christoph and Scherzinger, Stefanie and Schweikardt, Nicole and Stegmaier, Bernhard}, Bibsource = {DBLP, http://dblp.uni-trier.de}, Booktitle = {Proc. Int. Conf. Very Large Databases}, Conference-Abbr = {VLDB}, Crossref = {DBLP:conf/vldb/2004}, Ee = {http://www.vldb.org/conf/2004/RS6P2.PDF}, Keywords = {XML streaming buffer minimization event scheduling FluXQuery}, Pages = {228-239}, Pdf = {QueryEvaluation/XML/ProcessorsAndSystems/Streaming/Koch.Scherzinger.ea_FluXQueryT_VLDB_2004.pdf}, Title = {{Schema-based Scheduling of Event Processors and Buffer Minimization for Queries on Structured Data Streams}}, Url = {http://www.vldb.org/conf/2004/RS6P2.PDF}, Year = {2004}, Abstract = {We introduce an extension of the XQuery language, FluX, that supports event-based query processing and the conscious handling of main memory bu ers. Purely event-based queries of this language can be executed on streaming XML data in a very direct way. We then develop an algorithm that allows to e ciently rewrite XQueries into the event-based FluX language. This algorithm uses order constraints from a DTD to schedule event handlers and to thus minimize the amount of bu ering required for evaluating a query. We discuss the various technical aspects of query optimization and query evaluation within our framework. This is complemented with an experimental evaluation of our approach.}} @inproceedings{Koch_ComplexityNonRecXQ_PODS_2005, Author = {Koch, Christoph}, Booktitle = {Proc. ACM SIGMOD Symposium on Principles of Database Systems}, Conference-Abbr = {PODS}, Keywords = {XML XQuery complexit non-recursive}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/Comlexity/Koch_ComplexityNonRecXQ_PODS_2005.pdf}, Title = {{On the Complexity of Nonrecursive XQuery and Functional Query Languages on Complex Values}}, Url = {http://www.infosys.uni-sb.de/~koch/download/0503062.pdf}, Year = {2005}, Abstract = {This paper studies the complexity of evaluating functional query languages for complex values such as monad algebra and the recursion-free fragment of XQuery. We show that monad algebra with equality restricted to atomic values is complete for the class TA[2O(n),O(n)] of problems solvable in linear exponential time with a linear number of alternations. The monotone fragment of monad algebra with atomic value equality but without negation is complete for nondeterministic exponential time. For monad algebra with deep equality, we establish TA[2O(n),O(n)] lower and exponential-space upper bounds. Then we study a fragment of XQuery, Core XQuery, that seems to incorporate all the features of a query language on complex values that are traditionally deemed essential. A close connection between monad algebra on lists and Core XQuery (with ?child? as the only axis) is exhibited, and it is shown that these languages are expressively equivalent up to representation issues. We show that Core XQuery is just as hard as monad algebra w.r.t. combined complexity, and that it is in TC0 if the query is assumed fixed.}} @inproceedings{Koch_CompositionXQuery_WebDB_2005, Author = {Koch, Christoph}, Booktitle = {Proc. Int. Workshop on the Web and Databases}, Conference-Abbr = {WebDB}, Keywords = {XML XQuery composition expressiveness}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/Comlexity/Koch_CompositionXQuery_WebDB_2005.pdf}, Title = {{On the Role of Composition in XQuery}}, Url = {http://www-db.cs.uni-sb.de/~koch/download/webdb2005.pdf}, Year = {2005}, Abstract = {Nonrecursive XQuery is known to be hard for nondeterministic exponential time. Thus it is commonly believed that any algorithm for evaluating XQuery has to require exponential amounts of working memory and doubly exponential time in the worst case. In this paper we present a property - the lack of a certain form of composition - that virtually all real-world XQueries have and that allows for query evaluation in singly exponential time and polynomial space. Still, we are able to show for an important special case - our nonrecursive XQuery fragment restricted to atomic value equality - that the composition-free language is just as expressive as the language with composition. Thus, under widely-held complexity-theoretic assumptions, the composition-free language is an exponentially less succinct version of the language with composition.}} @inproceedings{Koch.Scherzinger.ea_FluXQuery_VLDB_2004, Author = {Koch, Christoph and Scherzinger, Stefanie and Schweikardt, Nicole and Stegmaier, Bernhard}, Bibsource = {DBLP, http://dblp.uni-trier.de}, Booktitle = {Proc. Int. Conf. on Very Large Databases}, Conference-Abbr = {VLDB}, Ee = {http://www.vldb.org/conf/2004/RS6P2.PDF}, Keywords = {XML XQuery stream implementation FluXQuery}, Pdf = {QueryEvaluation/XML/ProcessorsAndSystems/Streaming/Koch.Scherzinger.ea_FluXQuery_VLDB_2004.pdf}, Title = {{FluXQuery: An Optimizing XQuery Processor for Streaming XML Data}}, Url = {http://www.wit.at/people/scherzinger/documents/demo.pdf}, Year = {2004}, Abstract = {--}} @inproceedings{Krishnamurthy.Kaushik.ea_X2S_VLDB_2004, Author = {Krishnamurthy, Rajasekar and Kaushik, Raghav and Naughton, Jeffrey F.}, Bibsource = {DBLP, http://dblp.uni-trier.de}, Booktitle = {Proc. Int. Conf. on Very Large Databases}, Conference-Abbr = {VLDB}, Crossref = {DBLP:conf/vldb/2004}, Ee = {http://www.vldb.org/conf/2004/RS4P3.PDF}, Keywords = {XML translation relational SQL}, Pages = {144-155}, Pdf = {QueryEvaluation/XML/ProcessorsAndSystems/Translating/Krishnamurthy.Kaushik.ea_X2S_VLDB_2004.pdf}, Title = {{Efficient XML-to-SQL Query Translation: Where to Add the Intelligence?}}, Url = {http://www.vldb.org/conf/2004/RS4P3.PDF}, Year = {2004}, Abstract = {We consider the e ciency of queries generated by XML to SQL translation. We rst show that published XML-to-SQL query translation algorithms are suboptimal in that they often translate simple path expressions into complex SQL queries even when much simpler equivalent SQL queries exist. There are two logical ways to deal with this problem. One could generate suboptimal SQL queries using a fairly naive translation algorithm, and then attempt to optimize the resulting SQL; or one could use a more intelligent translation algorithm with the hopes of generating e cient SQL directly. We show that optimizing the SQL after it is generated is problematic, becoming intractable even in simple scenarios; by contrast, designing a translation algorithm that exploits information readily available at translation time is a promising alternative. To support this claim, we present a translation algorithm that exploits translation time information to generate e cient SQL for path expression queries over tree schemas.}} @inproceedings{Krishnamurthy.Chakaravarthy.ea_X2S_ICDE_2004, Address = {Washington, DC, USA}, Author = {Krishnamurthy, Rajasekar and Chakaravarthy, Venkatesan T. and Kaushik, Raghav and Naughton, Jeffrey F.}, Booktitle = {Proc. Int. Conf. on Data Engineering}, Conference-Abbr = {ICDE}, Isbn = {0-7695-2065-0}, Keywords = {XML translation XML query SQL recursive views}, Pages = {42}, Pdf = {QueryEvaluation/XML/ProcessorsAndSystems/Translating/Krishnamurthy.Chakaravarthy.ea_X2S_ICDE_2004.pdf}, Publisher = {IEEE Computer Society}, Title = {{Recursive XML Schemas, Recursive XML Queries, and Relational Storage: XML-to-SQL Query Translation}}, Url = {http://www.cs.wisc.edu/~sekar/research/recursiveqt.pdf}, Year = {2004}, Abstract = {We consider the problem of translating XML queries intoSQL when XML documents have been stored in an RDBMSusing a schema-based relational decomposition. Surprisingly,there is no published XML-to-SQL query translationalgorithm for this scenario that handles recursive XMLschemas. We present a generic algorithm to translate pathexpression queries into SQL in the presence of recursionin the schema and queries. This algorithm handles a generalclass of XML-to-Relational mappings, which includesall techniques proposed in literature. Some of the salientfeatures of this algorithm are: (i) It translates a path expressionquery into a single SQL query, irrespective of howcomplex the XML schema is, (ii) It uses the "with" clause inSQL99 to handle recursive queries even over non-recursiveschemas, (iii) It reconstructs recursive XML subtrees witha single SQL query and (iv) It shows that the support forlinear recursion in SQL99 is sufficient for handling pathexpression queries over arbitrarily complex recursive XMLschema.}} @inproceedings{Krishnamurthy.Kaushik.ea_2SDupl_WebDB_2004, Address = {New York, NY, USA}, Author = {Krishnamurthy, Rajasekar and Kaushik, Raghav and Naughton, Jeffrey F}, Booktitle = {Proc. Int. Workshop on the Web and Databases}, Conference-Abbr = {WebDB}, Doi = {http://doi.acm.org/10.1145/1017074.1017088}, Keywords = {XML translation SQL XML}, Location = {Paris, France}, Pages = {49--54}, Pdf = {QueryEvaluation/XML/ProcessorsAndSystems/Translating/Krishnamurthy.Kaushik.ea_2SDupl_WebDB_2004.pdf}, Publisher = {ACM Press}, Title = {{Unraveling the Duplicate-elimination Problem in XML-to-SQL Query Translation}}, Url = {http://webdb2004.cs.columbia.edu/papers/4-2.pdf}, Year = {2004}, Abstract = {We consider the scenario where existing relational data is exported as XML. In this context, we look at the problem of translating XML queries into SQL. XML query languages have two different notions of duplicates: node-identity based and value-based. Path expression queries have an implicit node-identity based duplicate elimination built into them. On the other hand, SQL only supports value-based duplicate elimination. In this paper, using a simple path expression query we illustrate the problems that arise when we attempt to simulate the node-identity based duplicate elimination using value-based duplicate elimination in the SQL queries. We show how a general solution for this problem covering the class of views considered in published literature requires a fairly complex mechanism.}} @inproceedings{Lam.Shui.ea_SkippingStrucJ_DASFA_2004, Author = {Lam, Franky and Shui, William M. and Fisher, Damien K. and Wong, Raymond K.}, Booktitle = {Int. Conf. on Database Systems for Advanced Applications}, Conference-Abbr = {DASFA}, Keywords = {XML XQuery structural joins algorithms efficient evaluation}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/StructuralJoins/Lam.Shui.ea_SkippingStrucJ_DASFA_2004.pdf}, Title = {{Skipping Strategies for Efficient Structural Joins}}, Url = {ftp://ftp.cse.unsw.edu.au/pub/doc/papers/UNSW/0320.pdf}, Year = {2004}, Abstract = {The structural join is considered a core operation in processing and optimizing XML queries. Various techniques have been proposed for efficiently finding structural relationships between a list of potential ancestors and a list of potential descendants. This paper presents a novel algorithm for efficiently processing structural joins. Moreover, previous work which performs well usually relies on external index structures such as a B-tree, which increases both the storage and memory overheads. Our proposal in this paper does not require any such data structures, and hence can be easily implemented and incorporated in any existing system. Experiments show that our method significantly outperforms previous algorithms.}} @inproceedings{Lechner.Preuner.ea_XQuery2XSLT_DASWIS_2002, Address = {London, UK}, Author = {Lechner, Stephan and Preuner, G{\"u}nter and Schrefl, Michael}, Booktitle = {Proc. Int. Workshop on Data Semantics in Web Information Systems}, Conference-Abbr = {DASWIS}, Isbn = {3-540-44122-0}, Keywords = {XML XQuery XSLT translation abstract machine}, Pages = {239--252}, Pdf = {QueryEvaluation/XML/ProcessorsAndSystems/Translating/Lechner.Preuner.ea_XQuery2XSLT_DASWIS_2002.pdf}, Publisher = {Springer-Verlag}, Title = {{Translating XQuery into XSLT}}, Url = {http://www.dke.jku.at/research/projects/xq2xsl/xq2xslDASWIS01.pdf}, Year = {2002}, Abstract = {The WWW Consortium (W3C) has recently presented a working draft of XQuery, which is intended to serve as standardized query language for XML. XQuery and other high-level query languages for XML documents are not yet implemented by commercial products. Yet many browsers have already built-in XSLT support for transforming XML documents. XSLT is a standard way of performing structural rearrangement or presentational transformation of XML documents, but formulating complex queries is, compared to XQuery, difficult and error-prone. If XQuery expressions could be translated into XSLT (e.g. by a translator written in Java or XSLT itself), the benefits of Xquery would be immediately available to a wide range of commercial products. This paper introduces a process for translating queries formulated in XQuery syntax into XSL stylesheets. The process is described independently from a particular implementation by means of an ASM (Abstract State Machine). The ASM traverses the parse tree of a particular query and translates each node into corresponding XSLT commands. The result of this translation process is an XSL stylesheet that can be applied to an XML document in order to perform the given query. The presented ASM can be easily coded in Java or XSLT to implement a prototype XQ2XSL translator.}} @inproceedings{Li.Ferreira.ea_CompileXML_ICS_2003, Address = {New York, NY, USA}, Author = {Li, Xiaogang and Ferreira, Renato and Agrawal, Gagan}, Booktitle = {Proc. Int. Conf. on Supercomputing}, Conference-Abbr = {ICS}, Doi = {http://doi.acm.org/10.1145/782814.782823}, Isbn = {1-58113-733-8}, Keywords = {XML XQuery compiler support query optimization}, Location = {San Francisco, CA, USA}, Pages = {42--52}, Publisher = {ACM Press}, Title = {{Compiler Support for Efficient Processing of XML Datasets}}, Url = {http://portal.acm.org/citation.cfm?id=782823}, Year = {2003}, Abstract = {Declarative, high-level, and/or application-class specific languages are often successful in easing application development. In this paper, we report our experiences in compiling a recently developed XML Query Language, XQuery for applications that process scientific datasets.Though scientific data processing applications can be conveniently represented in XQuery, compiling them to achieve efficient execution involves a number of challenges. These are, 1) analysis of recursive functions to identify reduction computations involving only associative and commutative operations, 2) replacement of recursive functions with iterative constructs, 3) parallelization of generalized reduction functions, which particularly requires the synthesis of global reduction functions, 4) application of data-centric transformations on the structure of XQuery, and 5) translation of XQuery processing to an imperative language like C/C++, which is required for using a middleware that offers low-level functionality.This paper describes our solutions towards these problems. By implementing the techniques in a compiler and generating code for a runtime system called Active Data Repository (ADR), we are able to achieve efficient processing of disk-resident datasets and parallelization on a cluster of machines. Our experimental results show that: 1) restructuring transformations, i.e. removing recursion and applying data-centric execution, result in several-folds improvement in performance, and 2) parallel versions achieve good load-balance, and incur no significant overheads besides communication.}} @inproceedings{Li.Yu.ea_Schema-FreeXQuery_VLDB_2004, Author = {Li, Yunyao and Yu, Cong and Jagadish, H. V.}, Bibsource = {DBLP, http://dblp.uni-trier.de}, Booktitle = {Proc. Int. Conf. on Very Large Data Bases}, Conference-Abbr = {VLDB}, Ee = {http://www.vldb.org/conf/2004/RS2P3.PDF}, Keywords = {XML XQuery schema-free lowest common ancestor approximate query}, Pages = {72-83}, Pdf = {QueryEvaluation/XML/LanguageConstructs/XQuery/Li.Yu.ea_Schema-FreeXQuery_VLDB_2004.pdf}, Title = {{Schema-Free XQuery}}, Url = {http://www.vldb.org/conf/2004/RS2P3.PDF}, Year = {2004}, Abstract = {The widespread adoption of XML holds out the promise that document structure can be exploited to specify precise database queries. However, the user may have only a limited knowledge of the XML structure, and hence may be unable to create a correct XQuery, particularly in the context of a heterogeneous information collection. The default is to use keyword-based search and we are all too familiar with how difficult it is to obtain precise answers by these means. We seek to address these problems by introducing the notion of Meaningful Lowest Common Ancestor Structure (MLCAS) for finding related nodes within an XML document. By automatically computing MLCAS and expanding ambiguous tag names, we add new functionalities to XQuery and enable users to take full advantage of XQuery in querying XML data precisely and efficiently without requiring (perfect) knowledge of the document structure. Such a Schema-Free XQuery is potentially of value not just in casual users with partial knowledge of schema, but also in a data integration or data evolution context where one would like a query written once to apply ?forever? as the schema of the data source changes. Our experimental evalua- tion found that it was possible to express a wide variety of queries in a Schema-Free manner and have them return correct results over a broad diversity of schemas. Furthermore, the evaluation of a Schema-Free query is not expensive using a novel stack-based algorithm we develop for computing MLCAS: from 1 to 4 times the execution time of an equivalent schema-aware query.}} @inproceedings{Liu.Vincent_XSLT2SQL_DEAS_2003, Author = {Liu, Jixue and Vincent, Millist}, Booktitle = {Proc. Int. Database Engineering and Applications Symposium}, Conference-Abbr = {DEAS}, Keywords = {XML XSLT relational implementation SQL query evaluation}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/XSLT/Liu.Vincent_Querytranslationfrom_DEAS_2003.pdf}, Title = {{Query Translation from XSLT to SQL}}, Url = {http://intl.ieeexplore.ieee.org/xpl/abs_free.jsp?arNumber=1214914}, Year = {2003}, Abstract = {XML has been accepted as a universal format for data interchange and publication. It can be applied in the applications in which the data of a database needs to be viewed in XML format so that the data being viewed takes more semantics and is easily understood. In these applications, the user of the data to be viewed sees only XML data, not the database. He may use XML query languages such as XSLT to query data and the retrieved data is presented in XML format to them. We are interested in the connection between the data that the user sees and the data in the database. More specifically, we are interested in translating XSLT queries to SQL queries.}} @article{Lu.Yu.ea_BenchmarkXMLDB_TOIS_2005, Address = {New York, NY, USA}, Author = {Lu, Hongjun and Yu, Jeffrey Xu and Wang, Guoren and Zheng, Shihui and Jiang, Haifeng and Yu, Ge and Zhou, Aoying}, Doi = {http://doi.acm.org/10.1145/1052934.1052940}, Issn = {1533-5399}, Journal = {ACM Transactions on Internet Technologies}, Journal-Abbr = {TOIS}, Keywords = {XML benchmarking query optimization processor XML databases}, Number = {1}, Pages = {154--194}, Pdf = {QueryEvaluation/XML/Lu.Yu.ea_BenchmarkXMLDB_TOIS_2005.pdf}, Publisher = {ACM Press}, Title = {{What Makes the Differences: Benchmarking XML Database Implementations}}, Url = {http://www.cs.ust.hk/~jianghf/files/bencharmk.pdf}, Volume = {5}, Year = {2005}, Abstract = {XML is emerging as a major standard for representing data on the World Wide Web. Recently, many XML storage models have been proposed to manage XML data. In order to assess an XML database's abilities to deal with XML queries, several benchmarks have also been proposed, including XMark and XMach. However, no reported studies using those benchmarks were found that can provide users with insights on the impacts of a variety of storage models on XML query performance. In this article, we report our first set of results on benchmarking a set of XML database implementations using two XML benchmarks. The selected implementations represent a wide range of approaches, including RDBMS-based systems with document-independent and document-dependent XML-relational schema mapping approaches, and XML native engines based on an Object-Oriented Model and the Document Object Model. Comprehensive experiments were conducted to study relative performance of different approaches and the important issues that affect XML query performance, such as path expression query processing, effectiveness of various partitioning, label-path, and indexing structures.}} @inproceedings{Lu.Chen.ea_TwigsLA_CIKM_2004, Address = {New York, NY, USA}, Author = {Lu, Jiaheng and Chen, Ting and Ling, Tok Wang}, Booktitle = {Proc. Conf. on Information and Knowledge Management}, Conference-Abbr = {CIKM}, Doi = {http://doi.acm.org/10.1145/1031171.1031272}, Isbn = {1-58113-874-1}, Keywords = {XML query processing twig joins structural joins query optimization}, Location = {Washington, D.C., USA}, Pages = {533--542}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/StructuralJoins/Lu.Chen.ea_TwigsLA_CIKM_2004.pdf}, Publisher = {ACM Press}, Title = {{Efficient Processing of XML Twig Patterns with Parent Child Edges: A Look-ahead Approach}}, Url = {http://portal.acm.org/citation.cfm?id=1031272}, Year = {2004}, Abstract = {With the growing importance of semi-structure data in information exchange, much research has been done to provide an effective mechanism to match a twig query in an XML database. A number of algorithms have been proposed recently to process a twig query holistically. Those algorithms are quite efficient for quires with only ancestor-descendant edges. But for queries with mixed ancestor-descendant and parent-child edges, the previous approaches still may produce large intermediate results, even when the input and output size are more manageable. To overcome this limitation, in this paper, we propose a novel holistic twig join algorithm, namely TwigStackList. Our main technique is to look-ahead read some elements in input data steams and cache limited number of them to lists in the main memory. The number of elements in any list is bounded by the length of the longest path in the XML document. We show that TwigStackList is I/O optimal for queries with only ancestor-descendant relationships below branching nodes. Further, even when queries contain parent-child relationship below branching nodes, the set of intermediate results in TwigStackList is guaranteed to be a subset of that in previous algorithms. We complement our experimental results on a range of real and synthetic data to show the significant superiority of TwigStackList over previous algorithms for queries with parent-child relationships.}} @inproceedings{Marx_FirstOrderPaths_ICDT_2005, Author = {Marx, Maarten}, Bibsource = {DBLP, http://dblp.uni-trier.de}, Booktitle = {Proc. Int. Conf. on Database Theory}, Conference-Abbr = {ICDT}, Ee = {http://springerlink.metapress.com/openurl.asp?genre=article{\&}issn=0302-9743{\&}volume=3363{\&}spage=114}, Keywords = {XML XPath completeness first-order logic conditional axes core xpath}, Pages = {114-128}, Pdf = {QueryEvaluation/XML/LanguageConstructs/XPath/Marx_FirstOrderPaths_ICDT_2005.pdf}, Title = {{First Order Paths in Ordered Trees}}, Url = {http://staff.science.uva.nl/~marx/pub/recent/icdt05.pdf}, Year = {2005}, Abstract = {We give two sufficient conditions on XPath like languages for having first order expressivity, meaning that every first order definable set of paths in an ordered node-labeled tree is definable in that XPath language. They are phrased in terms of expansions of navigational (sometimes called ?Core?) XPath. Adding either complementation, or the more elegant conditional paths is sufficient. A conditional path is an axis relation of the form (one step axis::n[F])+, denoting the transitive closure of the relation expressed by one step axis::n[F]. As neither is expressible in navigational XPath we also give characterizations in terms of first order logic of the answer sets and the sets of paths navigational XPath can define. The first in terms of a suitable two variable fragment, the second in terms of unions of conjunctive queries.}} @inproceedings{Marx_ConditionalXPathFirst_PODS_2004, Author = {Marx, Maarten}, Booktitle = {Proc. ACM Symposium on Principles of Database Systems}, Conference-Abbr = {PODS}, Keywords = {XPath Qualified Descendant Conditional Axes}, Month = {6}, Organization = {ACM}, Owner = {Tim Furche}, Pages = {13--22}, Pdf = {QueryEvaluation/XML/LanguageConstructs/XPath/Marx_ConditionalXPathFirst_PODS_2004.pdf}, Title = {{Conditional XPath, the First Order Complete XPath Dialect}}, Url = {http://turing.wins.uva.nl/~marx/pub/recent/pods04.pdf}, Year = {2004}, Abstract = {XPath is the W3C-standard node addressing language for XML documents. XPath is still under development and its technical aspects are intensively studied. What is missing at present is a clear characterization of the expressive power of XPath, be it either semantical or with reference to some well established existing (logical) formalism. Core XPath (the logical core of XPath 1.0 defined by Gottlob et al.) cannot express queries with conditional paths as exemplified by ?do a child step, while test is true at the resulting node.? In a first-order complete extension of Core XPath, such queries are expressible. We add conditional axis relations to Core XPath and show that the resulting language, called conditional XPath, is equally expressive as first-order logic when interpreted on ordered trees. Both the result, the extended XPath language, and the proof are closely related to temporal logic. Specifically, while Core XPath may be viewed as a simple temporal logic, conditional XPath extends this with (counterparts of) the since and until operators.}} @inproceedings{Marx_XPathwithConditional_EDBT_2004, Author = {Marx, Maarten}, Booktitle = {Proc. Extending Database Technology}, Conference-Abbr = {EDBT}, Keywords = {XPath Qualified Descendant Conditional Axes}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/LanguageConstructs/XPath/Marx_XPathwithConditional_EDBT_2004.pdf}, Title = {{XPath with Conditional Axis Relations}}, Url = {http://turing.wins.uva.nl/~marx/pub/edbt04.pdf}, Year = {2004}, Abstract = {This paper is about the W3C standard node-addressing language for XML documents, called XPath. XPath is still under development. Version 2.0 appeared in 2001 while the theoretical foundations of Version 1.0 (dating from 1998) are still being widely studied. The paper aims at bringing XPath to a ?stable fixed point? in its development: a version which is expressively complete, still manageable computationally, with a user-friendly syntax and a natural semantics. We focus on an important axis relation which is not expressible in XPath 1.0 and is very useful in practice: the conditional axis. With it we can express paths specified by for instance ?do a child step, while test is true at the resulting node?. We study the effect of adding conditional axis relations to XPath on its expressive power and the complexity of the query evaluation and query equivalence problems. We define an XPath dialect XCPath which is expressively complete, has a linear time query evaluation algorithm and for which query equivalence given a DTD can be decided in exponential time.}} @article{Marx.Rijke_SemanticCharacterizations_SIGR_2005, Author = {Marx, Maarten and de Rijke, Maarten}, Journal = {ACM SIGMOD Record}, Journal-Abbr = {SIGR}, Keywords = {XML XPath completeness first-order logic conditional XPath core XPath}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/LanguageConstructs/XPath/Marx.Rijke_SemanticCharacterizations_SIGR_2005.pdf}, Title = {{Semantic Characterizations of Navigational XPath}}, Url = {http://turing.wins.uva.nl/~marx/pub/recent/sigmod_record.pdf}, Year = {2005}, Abstract = {We give semantic characterizations of the expressive power of navigational XPath (a.k.a. Core XPath) in terms of first order logic. XPath can be used to specify sets of nodes and sets of paths in an XML document tree. We consider both uses. For sets of nodes, XPath is equally expressive as first order logic in two variables. For paths, XPath can be defined using four simple connectives, which together yield the class of first order definable relations which are safe for bisimulation. Furthermore, we give a characterization of the XPath expressible paths in terms of conjunctive queries.}} @inproceedings{May.Helmer.ea_XQueryNatix_XIME-P_2004, Author = {May, Norman and Helmer, Sven and Kanne, Carl-Christian and Moerkotte, Guido}, Booktitle = {Proc. of Int. Workshop on XQuery Implementation, Experience and Perspectives}, Conference-Abbr = {XIME-P}, Keywords = {XML XQuery Natix query optimization order processing}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/OrderDuplicates/May.Helmer.ea_XQueryNatix_XIME-P_2004.pdf}, Title = {{XQuery Processing in Natix with an Emphasis on Join Ordering}}, Url = {http://pi3.informatik.uni-mannheim.de/old/publications/ximep2004-joinorder.ps}, Year = {2004}, Abstract = {We give an overview on how XQuery processing works in our native XML database system Natix. After a brief description of the query compiler we focus on the aspect of join ordering when generating query execution plans. Here we show that better plans can be found when extending the search space of the plan generator.}} @inproceedings{May.Helmer.ea_NestedQueries_ICDE_2004, Author = {May, Norman and Helmer, Sven and Moerkotte, Guido}, Booktitle = {Proc. Int. Conf. on Data Engineering}, Conference-Abbr = {ICDE}, Keywords = {XML nested queries algebra query optimization}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/May.Helmer.ea_NestedQueries_ICDE_2004.pdf}, Title = {{Nested Queries and Quantifiers in an Ordered Context}}, Url = {http://pi3.informatik.uni-mannheim.de/old/publications/unnesting_icde2004.pdf}, Year = {2004}, Abstract = {We present algebraic equivalences that allow to unnest nested algebraic expressions for order-preserving algebraic operators. We illustrate how these equivalences can be applied successfully to unnest nested queries given in the XQuery language. Measurements illustrate the performance gains possible by unnesting.}} @inproceedings{May.Helmer.ea_QuantifiersXQuery_WISE_2003, Author = {May, Norman and Helmer, Sven and Moerkotte, Guido}, Booktitle = {Proc. Int. Conf. on Web Information Systems Engineering}, Conference-Abbr = {WISE}, Keywords = {XML XQuery quantifiers nested queries optimization rewriting}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/NestedQueries/May.Helmer.ea_QuantifiersXQuery_WISE_2003.pdf}, Title = {{Quantifiers in XQuery}}, Url = {http://pi3.informatik.uni-mannheim.de/~norman/unnesting_wise03.pdf}, Year = {2003}, Abstract = {We present algebraic equivalences that allow to unnest nested algebraic expressions containing quantifiers for order-preserving algebraic operators. We illustrate how these equivalences can be applied successfully to unnest nested queries formulated in XQuery. Measurements illustrate the performance gains possible by unnesting.}} @article{McHugh.Abiteboul.ea_Lore-SSDBMS_SIGRec_1997, Author = {McHugh, Jason and Abiteboul, Serge and Goldman, Roy and Quass, Dallan and Widom, Jennifer}, Journal = {SIGMOD Record}, Journal-Abbr = {SIGRec}, Keywords = {XML Lore semi-structured data database management algebra optimization graph-shaped}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/ProcessorsAndSystems/McHugh.Abiteboul.ea_Lore-SSDBMS_SIGRec_1997.pdf}, Title = {{Lore: A Database Management System for Semistructured Data}}, Url = {http://www-db.stanford.edu/lore/pubs/lore97.pdf}, Year = {1997}, Abstract = {Lore (for Lightweight Object Repository) is a DBMS designed specifically for managing semistructured information. Implementing Lore has required rethinking all aspects of a DBMS, including storage management, indexing, query processing and optimization, and user interfaces. This paper provides an overview of these aspects of the Lore system, as well as other novel features such as dynamic structural summaries and seamless access to data from external sources.}} @article{Meuss.Schulz_CAAs_TOIS_2001, Author = {Meuss, Holger and Schulz, Klaus U.}, Doi = {http://doi.acm.org/10.1145/382979.383042}, Issn = {1046-8188}, Journal = {ACM Transactions on Information Systems}, Journal-Abbr = {TOIS}, Keywords = {XML query languages visualization navigation browsing CAA complexity}, Number = {2}, Pages = {161--215}, Pdf = {QueryEvaluation/XML/Comlexity/Meuss.Schulz_CAAs_TOIS_2001.pdf}, Publisher = {ACM Press}, Title = {{Complete Answer Aggregates for Treelike Databases: A Novel Approach to Combine Querying and Navigation}}, Url = {http://www.cis.uni-muenchen.de/people/Meuss/Pub/TOIS01.pdf}, Volume = {19}, Year = {2001}, Abstract = {The use of markup languages like SGML, HTML or XML for encoding the strucutre of documents or linguistic data has lead to many databases where entries are adequately described as trees. In this context querying formalisms are interesting that offer the possiblity to refer both to textual content and logical structure. We consider models where the strucutre specified in a query is not only used as a filter, but also for selecting and presenting different parts of the data. If answers are formalized as mapping from query nodes to the database, a simple enumeration of all mappings in the answer set will often suffer from the effect that many answers have common subparts. From a theoretical point of view this may lead to an exponential time complexity of the computation and presentation of all answers. Concentration on the language of so called tree queries?a variant and extension of Kilpelinen's Tree Matching formalism?we introduce the notion of a ?complete answer aggregate? for a given query. This new data strucutre offers a compact view of the set of all answer and supports active exploration of the ansewer space. Since complete answer aggregates use a powerful structure-sharing mechanism their maximal size is of order &sgr;(d?h?q) where d and q respectively denote the size of the database and the query, and h is the maximal depth of a path of the database. An algorithm is given that computes a complete answer aggregate for a given treee query in time &sgr;(d?log(d)?h?). For the sublanguage of so-called rigid tree queries, as well as for so-called ?nonrecursive? databases, an improved bound of :&sgr;(d?log(d)?q) is obtained. The algorithm is based on a specific index structure that supports practical efficiency.}} @article{Miklau.Suciu_ContainmentEquivalence_JACM_2004, Address = {New York, NY, USA}, Author = {Miklau, Gerome and Suciu, Dan}, Doi = {http://doi.acm.org/10.1145/962446.962448}, Issn = {0004-5411}, Journal = {Journal of the ACM}, Journal-Abbr = {JACM}, Keywords = {XML XPath containment equivalence}, Number = {1}, Pages = {2--45}, Pdf = {QueryEvaluation/XML/Containment/Miklau.Suciu_ContainmentEquivalence_JACM_2004.pdf}, Publisher = {ACM Press}, Title = {{Containment and Equivalence for a Fragment of XPath}}, Url = {http://portal.acm.org/citation.cfm?id=962448}, Volume = {51}, Year = {2004}, Abstract = {XPath is a language for navigating an XML document and selecting a set of element nodes. XPath expressions are used to query XML data, describe key constraints, express transformations, and reference elements in remote documents. This article studies the containment and equivalence problems for a fragment of the XPath query language, with applications in all these contexts.In particular, we study a class of XPath queries that contain branching, label wildcards and can express descendant relationships between nodes. Prior work has shown that languages that combine any two of these three features have efficient containment algorithms. However, we show that for the combination of features, containment is coNP-complete. We provide a sound and complete algorithm for containment that runs in exponential time, and study parameterized PTIME special cases. While we identify one parameterized class of queries for which containment can be decided efficiently, we also show that even with some bounded parameters, containment remains coNP-complete. In response to these negative results, we describe a sound algorithm that is efficient for all queries, but may return false negatives in some cases.}} @inproceedings{ONeil.ONeil.ea_ORDPATH_SIGMOD_2004, Author = {O'Neil, Patrick and O'Neil, Elizabeth and Pal, Shankar and Cseri, Istvan and Schaller, Gideon and Westbury, Nigel}, Booktitle = {Proc. ACM SIGMOD Int. Conf. on Management of Data}, Conference-Abbr = {SIGMOD}, Doi = {http://doi.acm.org/10.1145/1007568.1007686}, Isbn = {1-58113-859-8}, Keywords = {XML encoding XQuery relational implementation}, Location = {Paris, France}, Pages = {903--908}, Pdf = {QueryEvaluation/XML/IndexingLabelling/ONeil.ONeil.ea_ORDPATH_SIGMOD_2004.pdf}, Publisher = {ACM Press}, Title = {{ORDPATHs: Insert-friendly XML Node Labels}}, Url = {http://www.cs.umb.edu/~poneil/ordpath.pdf}, Year = {2004}, Abstract = {We introduce a hierarchical labeling scheme called ORDPATH that is implemented in the upcoming version of Microsoft{\textregistered} SQL Server?. ORDPATH labels nodes of an XML tree without requiring a schema (the most general case---a schema simplifies the problem). An example of an ORDPATH value display format is "1.5.3.9.1". A compressed binary representation of ORDPATH provides document order by simple byte-by-byte comparison and ancestry relationship equally simply. In addition, the ORDPATH scheme supports insertion of new nodes at arbitrary positions in the XML tree, their ORDPATH values "careted in" between ORDPATHs of sibling nodes, without relabeling any old nodes.}} @inproceedings{Olteanu.Meuss.ea_XPathLF_XMLDM_2002, Author = {Olteanu, Dan and Meuss, Holger and Furche, Tim and Bry, Fran{\c c}ois}, Booktitle = {Proc. EDBT Workshop on XML-Based Data Management}, Conference-Abbr = {XMLDM}, Keywords = {XPath query rewriting query containment reverse axes}, Month = {3}, Pdf = {QueryEvaluation/XML/Containment/Olteanu.Meuss.ea_XPathLF_XMLDM_2002.pdf}, Publisher = {Springer-Verlag}, Series = {LNCS}, Title = {{XPath: Looking Forward}}, Url = {http://www.pms.ifi.lmu.de/publikationen/#PMS-FB-2002-4}, Urldate = {2004/11/11}, Volume = {2490}, Year = {2002}, Abstract = {The location path language XPath is of particular importance for XML applications since it is a core component of many XML processing standards such as XSLT or XQuery. In this paper, based on axis symmetry of XPath, equivalences of XPath 1.0 location paths involving ?reverse axes?, such as ancestor and preceding, are established. These equivalences are used as rewriting rules in an algorithm for transforming location paths with reverse axes into equivalent reverse-axis-free ones. Location paths without reverse axes as generated by the presented rewriting algorithm enable efficient SAX-like streamed data processing of XPath.}} @inproceedings{Ordonez_RecursiveSQL_SIGMOD_2005, Address = {New York, NY, USA}, Author = {Ordonez, Carlos}, Booktitle = {Proc. ACM SIGMOD Int. Conf. on Management of Data}, Conference-Abbr = {SIGMOD}, Doi = {http://doi.acm.org/10.1145/1066157.1066260}, Isbn = {1-59593-060-4}, Keywords = {SQL recursive queries}, Location = {Baltimore, Maryland}, Pages = {834--839}, Pdf = {QueryEvaluation/RecursiveQueries/Ordonez_RecursiveSQL_SIGMOD_2005.pdf}, Publisher = {ACM Press}, Title = {{Optimizing Recursive Queries in SQL}}, Url = {http://portal.acm.org/citation.cfm?id=1066157.1066260}, Year = {2005}, Abstract = {Recursion represents an important addition to the SQL language. This work focuses on the optimization of linear recursive queries in SQL. To provide an abstract framework for discussion, we focus on computing the transitive closure of a graph. Three optimizations are studied: (1) Early evaluation of row selection conditions. (2) Eliminating duplicate rows in intermediate tables. (3) Defining an enhanced index to accelerate join computation. Optimizations are evaluated on two types of graphs: binary trees and sparse graphs. Binary trees represent an ideal graph with no cycles and a linear number of edges. Sparse graphs represent an average case with some cycles and a linear number of edges. In general, the proposed optimizations produce a significant reduction in the evaluation time of recursive queries.}} @inproceedings{Page.Hidders.ea_NodeConstr_WebDB_2005, Author = {Page, Wim Le and Hidders, Jan and Michiels, Philippe and Paredaens, Jan and Vercammen, Roel}, Booktitle = {Proc. Int. Workshop on the Web and Databases}, Conference-Abbr = {WebDB}, Keywords = {XML XQuery node construction expressive power}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/Comlexity/Page.Hidders.ea_NodeConstr_WebDB_2005.pdf}, Title = {{On the Expressive Power of Node Construction in XQuery}}, Url = {http://www.adrem.ua.ac.be/~rvcamm/publications/WebDB2005.pdf}, Year = {2005}, Abstract = {In the relational model it has been shown that the flat relational algebra has the same expressive power as the nested relational algebra, as far as queries over flat relations and with flat results are concerned [6]. Hence, for each query that uses the nested relational model and that, with a flat table as input always has a flat table as output, there exists an equivalent flat query that only uses the flat relational model. In analogy, we study a related flat-flat problem for XQuery: for each expression containing operations that construct new nodes and whose XML result contains only original nodes, there exists an equivalent ?flat? expression in XQuery that does not construct new nodes.}} @inproceedings{Paparizos.AlKhalifa.ea_GroupingXML_XMLDM_2002, Author = {Paparizos, Stelios and Al-Khalifa, Shurug and Jagadish, H. V. and Lakshmanan, Laks V.S. and Nierman, Andrew and Srivastava, Divesh and Wu, Yuqing}, Booktitle = {EDBT Workshop on XML Data Management}, Conference-Abbr = {XMLDM}, Keywords = {XQuery, grouping, query optimization, algebra, TAX, XML}, Number = {2490}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/LanguageConstructs/XQuery/Paparizos.AlKhalifa.ea_GroupingXML_XMLDM_2002.pdf}, Publisher = {Springer-Verlag}, Series = {LNCS}, Title = {{Grouping in XML}}, Url = {http://www.cs.indiana.edu/~yuqwu/papers/XMLDB02-Grouping.pdf}, Year = {2002}, Abstract = {XML permits repeated and missing sub-elements, and missing attributes. We discuss the consequent implications on grouping, both with respect to specification and with respect to implementation. The techniques described here have been implemented in the TIMBER native XML database system being developed at the University of Michigan.}} @techreport{Paparizos.Al-Khalifa.ea_TIMBERPhysAlg_TR_2002, Author = {Paparizos, Stelios and Al-Khalifa, Shurug and Jagadish, H.V. and Nierman, Andrew and Wu, Yuqing}, Institution = {EECS Department, Univ. of Michigan}, Keywords = {XML TIMBER physical algebra TAX}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/Paparizos.Al-Khalifa.ea_TIMBERPhysAlg_TR_2002.pdf}, Title = {{A Physical Algebra for XML}}, Url = {http://www.eecs.umich.edu/db/timber/files/physical.pdf}, Year = {2002}, Abstract = {We present a physical algebra for the manipulation of XML in a database. We show how to map logical algebra operators to this physical algebra. We also present several physical algebra identities that are useful for query optimization. This physical algebra is the basis for the implementation of the TIMBER native XML database system at the University of Michigan.}} @inproceedings{Paparizos.Jagadish_SetsVsSequences_VLDB_2005, Author = {Paparizos, Stelios and Jagadish, H.V.}, Booktitle = {Proc. Int. Conf. on Very Large Databases}, Conference-Abbr = {VLDB}, Keywords = {XML ordering algebra query optimization TLC}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/Paparizos.Jagadish_SetsVsSequences_VLDB_2005.pdf}, Title = {{Pattern tree algebras: sets or sequences?}}, Url = {http://www.eecs.umich.edu/db/timber/files/ordervldb05.pdf}, Year = {2005}, Abstract = {XML and XQuery semantics are very sensitive to the order of the produced output. Although pattern-tree based algebraic approaches are becoming more and more popular for evaluating XML, there is no universally accepted technique which can guarantee both a correct output order and a choice of efficient alternative plans. We address the problem using hybrid collections of trees that can be either sets or sequences or something in between. Each such collection is coupled with an Ordering Specification that describes how the trees are sorted (full, partial or no order). This provides us with a formal basis for developing a query plan having parts that maintain no order and parts with partial or full order. It turns out that duplicate elimination introduces some of the same issues as order maintenance: it is expensive and a single collection type does not always provide all the flexibility required to optimize this properly. To solve this problem we associate with each hybrid collection a Duplicate Specification that describes the presence or absence of duplicate elements in it. We show how to extend an existing bulk tree algebra, TLC [12], to use Ordering and Duplicate specifications and produce correctly ordered results. We also suggest some optimizations enabled by the flexibility of our approach, and experimentally demonstrate the performance increase due to them.}} @inproceedings{Paparizos.Wu.ea_TreeLogical_SIGMOD_2004, Author = {Paparizos, Stelios and Wu, Yuqing and Lakshmanan, Laks V. S. and Jagadish, H. V.}, Booktitle = {Proc. ACM SIGMOD Conf. on Management of Data}, Conference-Abbr = {SIGMOD}, Doi = {http://doi.acm.org/10.1145/1007568.1007579}, Isbn = {1-58113-859-8}, Keywords = {XML XQuery optimization tree locical classes efficiency}, Location = {Paris, France}, Pages = {71--82}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/Paparizos.Wu.ea_TreeLogical_SIGMOD_2004.pdf}, Publisher = {ACM Press}, Title = {{Tree Logical Classes for Efficient Evaluation of XQuery}}, Url = {http://www.cs.indiana.edu/~yuqwu/papers/SIGMOD04-TLC.pdf}, Year = {2004}, Abstract = {XML is widely praised for its flexibility in allowing repeated and missing sub-elements. However, this flexibility makes it challenging to develop a bulk algebra, which typically manipulates sets of objects with identical structure. A set of XML elements, say of type book, may have members that vary greatly in structure, e.g. in the number of author sub-elements. This kind of heterogeneity may permeate the entire document in a recursive fashion: e.g., different authors of the same or different book may in turn greatly vary in structure. Even when the document conforms to a schema, the flexible nature of schemas for XML still allows such significant variations in structure among elements in a collection. Bulk processing of such heterogeneous sets is problematic.In this paper, we introduce the notion of logical classes (LC) of pattern tree nodes, and generalize the notion of pattern tree matching to handle node logical classes. This abstraction pays off significantly in allowing us to reason with an inherently heterogeneous collection of elements in a uniform, homogeneous way. Based on this, we define a Tree Logical Class (TLC) algebra that is capable of handling the heterogeneity arising in XML query processing, while avoiding redundant work. We present an algorithm to obtain a TLC algebra expression from an XQuery statement (for a large fragment of XQuery). We show how to implement the TLC algebra efficiently, introducing the nest-join as an important physical operator for XML query processing. We show that evaluation plans generated using the TLC algebra not only are simpler but also perform better than those generated by competing approaches. TLC is the algebra used in the Timber [8] system developed at the University of Michigan.}} @inproceedings{Park.Min.ea_FunInlStrRecXQ_VLDB_2002, Author = {Park, Chang-Won and Min, Jun-Ki and Chung, Chin-Wan}, Bibsource = {DBLP, http://dblp.uni-trier.de}, Booktitle = {Proc. Int. Conf. on Very Large Databases}, Conference-Abbr = {VLDB}, Ee = {http://www.vldb.org/conf/2002/S04P01.pdf}, Keywords = {XML XQuery function inlining structurally recursive queries}, Pages = {83-94}, Pdf = {QueryEvaluation/XML/Compilation/Park.Min.ea_FunInlStrRecXQ_VLDB_2002.pdf}, Title = {{Structural Function Inlining Technique for Structurally Recursive XML Queries}}, Url = {http://www.vldb.org/conf/2002/S04P01.pdf}, Year = {2002}, Abstract = {Structurally recursive XML queries are an important query class that follows the structure of XML data. At present, it is difficult for XQuery to type and optimize structurally recursive queries because of polymorphic recursive functions involved in the queries. In this paper, we propose a new technique called structural function inlining which inlines recursive functions used in a query by making good use of available type information. Based on the technique, we develop a new approach to typing and optimizing structurally recursive queries. The new approach yields a more precise result type for a query. Furthermore, it produces an optimal algebraic expression for the query with respect to the type information. When a structurally recursive query is applied to non-recursive XML data, our approach translates the query into a finitely nested iterations. We conducted several experiments with commonly used real-life and synthetic datasets. The experimental results show that the number of node lookups by our approach is on the average 3.7 times and up to 279.8 times smaller than that by the XQuery core?s current approach in evaluating structurally recursive queries.}} @inproceedings{Pirahesh.Kleewein.ea_SystemRX_SIGMOD_2005, Author = {Pirahesh, Mir Hamid and Kleewein, Jim and Cochrane, Roberta J. and Ozcan, Fatma and Beyer, Kevin S. and Josifovski, Vanja and Lapis, George and Lohman, Guy M. and Lyle, Bob and Seemann, Normen and Truong, Tuong and der Linden, Bert Van and Vickery, Brian and Zhang, Chun}, Booktitle = {Proc. ACM SIGMOD Int Conf. on Management of Data}, Conference-Abbr = {SIGMOD}, Keywords = {XML relational database System RX}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/ProcessorsAndSystems/Pirahesh.Kleewein.ea_SystemRX_SIGMOD_2005.pdf}, Title = {{System RX: One Part Relational, One Part XML}}, Url = {http://www-db.stanford.edu/~widom/cs346/ozcan-paper1.pdf}, Year = {2005}, Abstract = {This paper describes the overall architecture and design aspects of a hybrid relational and XML database system called System RX. We believe that such a system is fundamental in the evolution of enterprise data management solutions: XML and relational data will co-exist and complement each other in enterprise solutions. Furthermore, a successful XML repository requires much of the same infrastructure that already exists in a relational database management system. Finally, XML query languages have con-siderable conceptual and functional overlap with relational data-flow engines. System RX is the first truly hybrid system that co-mingles XML and relational data, giving them equal footing. The new support for XML includes native support for storage and indexing as well as query compilation and evaluation support for the latest industry-standard query languages, SQL/XML and XQuery. By building a hybrid system, we leverage more than 20 years of data management research to advance XML technology to the same standards expected from mature relational systems.}} @inproceedings{Ramanan_MinimizingTreePat_SIGMOD_2002, Address = {New York, NY, USA}, Author = {Ramanan, Prakash}, Booktitle = {Proc. ACM SIGMOD Int. Conf. on Management of Data}, Conference-Abbr = {SIGMOD}, Doi = {http://doi.acm.org/10.1145/564691.564726}, Isbn = {1-58113-497-5}, Keywords = {XML tree patterns minimizing efficient algorithm}, Location = {Madison, Wisconsin}, Pages = {299--309}, Pdf = {QueryEvaluation/XML/Containment/Ramanan_MinimizingTreePat_SIGMOD_2002.pdf}, Publisher = {ACM Press}, Title = {{Efficient Algorithms for Minimizing Tree Pattern Queries}}, Url = {http://www.cs.wichita.edu/~ramanan/PAPERS/querymin.PDF}, Year = {2002}, Abstract = {We consider the problem of minimizing tree pattern queries (TPQ) that arise in XML and in LDAP-style network directories. In [Minimization of Tree Pattern Queries, Proc. ACM SIGMOD Intl. Conf. Management of Data, 2001, pp. 497-508], Amer-Yahia, Cho, Lakshmanan and Srivastava presented an O(n4) algorithm for minimizing TPQs in the absence of integrity constraints (Case 1); n is the number of nodes in the query. Then they considered the problem of minimizing TPQs in the presence of three kinds of integrity constraints: required-child, required-descendant and subtype (Case 2). They presented an O(n6) algorithm for minimizing TPQs in the presence of only required-child and required-descendant constraints (i.e., no subtypes allowed; Case 3). We present O(n2), O(n4) and O(n2) algorithms for minimizing TPQs in these three cases, respectively, based on the concept of graph simulation. We believe that our O(n2) algorithms for Cases 1 and 3 are runtime optimal.}} @inproceedings{Rao.Moon_PRIXIndex_ICDE_2004, Author = {Rao, Praveen R. and Moon, Bongki}, Booktitle = {Proc. Int. Conf. on Data Engineering}, Conference-Abbr = {ICDE}, Keywords = {XML PRIX indexing}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/IndexingLabelling/Rao.Moon_PRIXIndex_ICDE_2004.pdf}, Title = {{PRIX: Indexing and Querying XML Using Prufer Sequences}}, Url = {http://www.cs.ucr.edu/~tsotras/cs267/prix.pdf}, Year = {2004}, Abstract = {We propose a new way of indexing XML documents and processing twig patterns in an XML database. Every XML document in the database can be transformed into a sequence of labels by Pr{\"u}fer?s method that constructs a one-to-one correspondence between trees and sequences. During query processing, a twig pattern is also transformed into its Pr{\"u}fer sequence. By performing subsequence matching on the set of sequences in the database, and performing a series of refinement phases that we have developed, we can find all the occurrences of a twig pattern in the database. Our approach allows holistic processing of a twig pattern without breaking the twig into root-to-leaf paths and processing these paths individually. Furthermore, we show in the paper that all correct answers are found without any false dismissals or false alarms. Experimental results demonstrate the performance benefits of our proposed techniques.}} @inproceedings{Sahuguet.Alexe_SubdocumentQueries_WWW_2005, Address = {New York, NY, USA}, Author = {Sahuguet, Arnaud and Alexe, Bogdan}, Booktitle = {Proc. Int. Conf. on World Wide Web}, Conference-Abbr = {WWW}, Doi = {http://doi.acm.org/10.1145/1060745.1060787}, Isbn = {1-59593-046-9}, Keywords = {XML XQuery sub-documents identity querying}, Location = {Chiba, Japan}, Pages = {268--277}, Pdf = {QueryEvaluation/XML/LanguageConstructs/XQuery/Sahuguet.Alexe_SubdocumentQueries_WWW_2005.pdf}, Publisher = {ACM Press}, Title = {{Sub-document Queries over XML with XSQirrel}}, Url = {http://portal.acm.org/citation.cfm?id=1060787}, Year = {2005}, Abstract = {This paper describes XSQirrel, a new XML query language that transforms a document into a sub-document, i.e. a tree where the root-to-leaf paths are a subset of the root-to-leaf paths from the original document.We show that this type of queries is extremely useful for various applications (e.g. web services) and that the currently existing query languages are poorly equipped to express, reason and evaluate such queries. In particular, we emphasize the need to be able to compose such queries. We present the XSQirrel language with its syntax, semantics and two language specific operators, union and composition.For the evaluation of the language, we leverage well established query technologies by translating XSQirrel expressions into XPath programs, XQuery queries or XSLT stylesheets.We provide some experimental results that compare our various evaluation strategies. We also show the runtime benefits of query composition over sequential evaluation.}} @inproceedings{Schenkel.Theobald.ea_HOPI_EDBT_2004, Author = {Schenkel, R. and Theobald, A. and Weikum, G.}, Booktitle = {Proc. Extending Database Technology}, Conference-Abbr = {EDBT}, Date-Added = {2005-05-01 22:42:02 +0200}, Date-Modified = {2005-05-01 22:43:08 +0200}, Keywords = {XML indexing graph transitive closure HOPI}, Pdf = {QueryEvaluation/XML/IndexingLabelling/Schenkel.Theobald.ea_HOPI_EDBT_2004.pdf}, Title = {{HOPI: An Efficient Connection Index for Complex XML Document Collections}}, Url = {http://wwwcs.uni-paderborn.de/cs/ag-boettcher/lehre/SS04/seminar/download/edbt04.HOPI.An.Efficient.Connection.Index.for.Complex.XML.Document.Collections.pdf}, Year = {2004}, Abstract = {In this paper we present HOPI, a new connection index for XML documents based on the concept of the 2?hop cover of a directed graph introduced by Cohen et al. In contrast to most of the prior work on XML indexing we consider not only paths with child or parent relationships between the nodes, but also provide space? and time?efficient reachability tests along the ancestor, descendant, and link axes to support path expressions with wildcards in our XXL search engine. We improve the theoretical concept of a 2?hop cover by developing scalable methods for index creation on very large XML data collections with long paths and extensive cross?linkage. Our experiments show substantial savings in the query performance of the HOPI index over previously proposed index structures in combination with low space requirements.}} @inproceedings{Schenkel.Theobald.ea_EfficientHOPI_ICDE_2005, Author = {Schenkel, Ralf and Theobald, Anja and Weikum, Gerhard}, Booktitle = {Proc. Int. Conf. on Data Engineering}, Conference-Abbr = {ICDE}, Keywords = {XML indexing HOPI transitive closure}, Owner = {Tim Furche}, Pages = {360-371}, Pdf = {QueryEvaluation/XML/IndexingLabelling/Schenkel.Theobald.ea_EfficientHOPI_ICDE_2005.pdf}, Title = {{Efficient Creation and Incremental Maintenance of the HOPI Index for Complex XML Document Collections}}, Url = {http://doi.ieeecomputersociety.org/10.1109/ICDE.2005.57}, Year = {2005}, Abstract = {The HOPI index, a connection index for XML documents based on the concept of a 2?hop cover, provides space? and time?efficient reachability tests along the ancestor, descendant, and link axes to support path expressions with wildcards in XML search engines. This paper presents enhanced algorithms for building HOPI, shows how to augment the index with distance information, and discusses incremental index maintenance. Our experiments show substantial improvements over the existing divide-and-conquer algorithm for index creation, low space overhead for including distance information in the index, and efficient updates.}} @inproceedings{Schott.Noga_LazyXSLT_DocEng_2003, Author = {Schott, Steffen and Noga, Markus L.}, Booktitle = {Proc. ACM Symposium on Document Engineering}, Conference-Abbr = {DocEng}, Doi = {http://doi.acm.org/10.1145/958220.958224}, Isbn = {1-58113-724-9}, Keywords = {XML XSLT evaluation lazy query languages processing}, Location = {Grenoble, France}, Pages = {9--18}, Pdf = {QueryEvaluation/XML/ProcessorsAndSystems/Schott.Noga_LazyXSLT_DocEng_2003.pdf}, Publisher = {ACM Press}, Title = {{Lazy XSL Transformations}}, Url = {http://portal.acm.org/citation.cfm?id=958224}, Year = {2003}, Abstract = {We introduce a lazy XSLT interpreter that provides random access to the transformation result. This allows efficient pipelining of transformation sequences. Nodes of the result tree are computed only upon initial access. As these computations have limited fan-in, sparse output coverage propagates backwards through the pipeline.In comparative measurements with traditional eager implementations, our approach is on par for complete coverage and excels as coverage becomes sparser. In contrast to eager evaluation, lazy evaluation also admits infinite intermediate results, thus extending the design space for transformation sequences.To demonstrate that lazy evaluation preserves the semantics of XSLT, we reduce XSLT to the lambda calculus via a functional language. While this is possible for all languages, most imperative languages cannot profit from the confluence of lambda as only one reduction applies at a time.}} @article{Schwentick_XPathContainment_SIGR_2004, Address = {New York, NY, USA}, Author = {Schwentick, Thomas}, Date-Modified = {2006-02-01 17:30:30 +0100}, Doi = {http://doi.acm.org/10.1145/974121.974140}, Issn = {0163-5808}, Journal = {SIGMOD Record}, Journal-Abbr = {SIGR}, Keywords = {XML XPath query containment query optimization language properties}, Number = {1}, Pages = {101--109}, Pdf = {QueryEvaluation/XML/Containment/Schwentick_XPathContainment_SIGR_2004.pdf}, Publisher = {ACM Press}, Title = {{XPath Query Containment}}, Url = {http://portal.acm.org/citation.cfm?id=974140}, Volume = {33}, Year = {2004}, Abstract = {Consider an XML publish-subscribe scenario with hundreds of subscribers and tens of thousands of XML documents to be delivered per day. Subscribers specify the documents in which they are interested in by means of XPath [8] expressions. If an expression matches a (part of a) document it is delivered to the subscriber. Naturally, it is desired that the decision to which subscriber a document must be sent should be taken quickly. Although the test whether a single XPath expression matches can be done in polynomial time, it is not efficient to test every such expression for every document. Fortunately, there is a partial order on expressions, i.e., for some expressions p; q it might hold that whenever a document matches p it also matches q (denoted p 0 q). If we already know that a document matches p, we do not need to test q anymore, as it matches automatically. Correspond- ingly, if we know that q does not match then p will not match either. Hence, the inclusion structure of the XPath expressions should be computed in advance to decrease online computation time. This leads to the algorithmic problem of XPath Query Containment, i.e., checking whether p 0 q (for a different, index- based approach see, e.g., [6]).}} @inproceedings{Silberstein.He.ea_BOXesLabel_ICDE_2005, Author = {Silberstein, Adam and He, Hao and Yi, Ke and Yang, Jun}, Bibsource = {DBLP, http://dblp.uni-trier.de}, Booktitle = {Proc. Int. Conf. on Data Engineering}, Conference-Abbr = {ICDE}, Crossref = {DBLP:conf/icde/2005}, Ee = {http://csdl.computer.org/comp/proceedings/icde/2005/2285/00/22850285abs.htm}, Keywords = {XML labeling indexing boxes maintenance}, Pages = {285-296}, Pdf = {QueryEvaluation/XML/IndexingLabelling/Silberstein.He.ea_BOXesLabel_ICDE_2005.pdf}, Title = {{BOXes: Efficient Maintenance of Order-Based Labeling for Dynamic XML Data}}, Url = {http://www.cs.duke.edu/dbgroup/papers/2005-ICDE-shyy-xmlorder.pdf}, Year = {2005}, Abstract = {Order-based element labeling for tree-structured XML data is an important technique in XML processing. It lies at the core of many fundamental XML operations such as containment join and twig matching. While labeling for static XML documents is well understood, less is known about how to maintain accurate labeling for dynamic XML documents, when elements and subtrees are inserted and deleted. Most existing approaches do not work well for arbitrary update patterns; they either produce unacceptably long labels or incur enormous relabeling costs. We present two novel I/O-efficient data structures, W-BOX and B-BOX, that efficiently maintain labeling for large, dynamic XML documents. We show analytically and experimentally that both, despite consuming minimal amounts of storage, gracefully handle arbitrary update patterns without sacrificing lookup efficiency. The two structures together provide a nice tradeoff between update and lookup costs: W-BOX has logarithmic amortized update cost and constant worst-case lookup cost, while B-BOX has constant amortized update cost and logarithmic worst-case lookup cost. We further propose techniques to eliminate the lookup cost for read-heavy workloads.}} @inproceedings{Stefanescu.Thomo.ea_DistribGPQ_SAC_2005, Address = {New York, NY, USA}, Author = {Stefanescu, Dan C. and Thomo, Alex and Thomo, Lida}, Booktitle = {Proc. ACM Symposium on Applied Computing}, Conference-Abbr = {SAC}, Doi = {http://doi.acm.org/10.1145/1066677.1066819}, Isbn = {1-58113-964-0}, Keywords = {XML general path expressions XPath distributed evaluation}, Location = {Santa Fe, New Mexico}, Pages = {610--616}, Pdf = {QueryEvaluation/XML/ProcessorsAndSystems/Stefanescu.Thomo.ea_DistribGPQ_SAC_2005.pdf}, Publisher = {ACM Press}, Title = {{Distributed Evaluation of Generalized Path Queries}}, Url = {http://portal.acm.org/citation.cfm?id=1066677.1066819}, Year = {2005}, Abstract = {Nowadays, we are required to deal with more complex data, prime examples of which are data on the Web, XML data, biological data, etc. There are already proposed abstractions to handle these kinds of data, in particular in terms of semistructured data models. A semistructured model conceives a database essentially as a finite directed labeled graph whose nodes represent objects, and whose edges represent relationships between objects. In this paper, we focus on path queries, which are considered the basic querying mechanism for semistructured data. In essence, such queries are used to navigate, or discover paths that conform to specifications captured by regular expressions. In order to make the navigation more useful, we consider generalized path queries, in which the symbols could optionally be weighted by numbers. Such numbers can express a variety of information about the data that the query could possibly match or navigate.Motivated by the plethora of today's applications utilizing Web services and peer-to-peer architectures, we present a distributed algorithm for evaluating generalized path queries. We follow a realistic model with distributed (non-shared) memory and message-passing between processors. An optimal solution to the problem lies in the intersection of ideas related to distributed query evaluation, distributed shortest path computation, and queueing systems.}} @inproceedings{Trombetta.Montesi_EquivalencesXSLT_IDEAS_2004, Author = {Trombetta, Alberto and Montesi, Danilo}, Booktitle = {Proc. Int. Database Engineering and Applications Symposium}, Conference-Abbr = {IDEAS}, Keywords = {XML XSLT query languages optimization equivalence}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/Containment/Trombetta.Montesi_EquivalencesXSLT_IDEAS_2004.pdf}, Title = {{Equivalences and Optimizations in an Expressive XSLT Fragment}}, Url = {http://csdl.computer.org/dl/proceedings/ideas/2004/2168/00/21680171.pdf}, Year = {2004}, Abstract = {XML is the standard data interchange format and XSLT is the W3C proposed standard for transforming and restructuring XML documents. It turns out that XSLT has very powerful query capabilities as well. However, due to its complex syntax and lack of formal specification, it is not a trivial task to decide whether two XSLT stylesheets yield the same result, even if for an XSLT fragment. We isolate such fragment, powerful enough for expressing several interesting queries and for manipulating XML documents and show how to translate them into queries expressed in a properly extended version of TAX, a powerful XML query algebra, for which we provide a collection of equivalence rules. It is then possible to reason about XSLT equivalences, by translating XSLT queries into XTAX queries and then statically verifying their equivalence, by means of the mentioned equivalence rules.}} @inproceedings{Vagena.Moro.ea_TwigGraphs_WebDB_2004, Address = {New York, NY, USA}, Author = {Vagena, Zografoula and Moro, Mirella M. and Tsotras, Vassilis J.}, Booktitle = {Proc. Int. Workshop on the Web and Databases}, Conference-Abbr = {WebDB}, Doi = {http://doi.acm.org/10.1145/1017074.1017087}, Keywords = {XML twig joins structural joins graph-shaped}, Location = {Paris, France}, Pages = {43--48}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/StructuralJoins/Vagena.Moro.ea_TwigGraphs_WebDB_2004.pdf}, Publisher = {ACM Press}, Title = {{Twig Query Processing over Graph-Structured XML Data}}, Url = {http://webdb2004.cs.columbia.edu/papers/4-1.pdf}, Year = {2004}, Abstract = {XML and semi-structured data is usually modeled using graph structures. Structural summaries, which have been proposed to speedup XML query processing have graph forms as well. The existent approaches for evaluating queries over tree structured data (i.e. data whose underlying structure is a tree) are not directly applicable when the data is modeled as a random graph. Moreover, they cannot be applied when structural summaries are employed and, to the best of our knowledge, no analogous techniques have been reported for this case either. As a result, the potential of structural summaries is not fully exploited.In this paper, we investigate query evaluation techniques applicable to graph-structured data. We propose efficient algorithms for the case of directed acyclic graphs, which appear in many real world situations. We then tailor our approaches to handle other directed graphs as well. Our experimental evaluation reveals the advantages of our solutions over existing methods for graph-structured data.}} @inproceedings{Villard.Layaida_IncrementalXSLT_WWW_2002, Author = {Villard, Lionel and Laya{\"\i}da, Nabil}, Booktitle = {Proc. Int. World Wide Web Conf.}, Conference-Abbr = {WWW}, Doi = {http://doi.acm.org/10.1145/511446.511508}, Isbn = {1-58113-449-5}, Keywords = {XML XSLT incremental query evaluation languages}, Location = {Honolulu, Hawaii, USA}, Pages = {474--485}, Pdf = {QueryEvaluation/XML/ProcessorsAndSystems/Villard.Layaida_IncrementalXSLT_WWW_2002.pdf}, Publisher = {ACM Press}, Title = {{An Incremental XSLT Transformation Processor for XML Document Manipulation}}, Url = {http://www.research.ibm.com/people/v/villard/Papiers/incXSLT.pdf}, Year = {2002}, Abstract = {In this paper, we present an incremental transformation framework called incXSLT. This framework has been experimented for the XSLT language defined at the World Wide Web Consortium. For the currently available tools, designing the XML content and the transformation sheets is an inefficient, a tedious and an error prone experience. Incremental transformation processors such as incXSLT represent a better alternative to help in the design of both the content and the transformation sheets. We believe that such frameworks are a first step toward fully interactive transformation-based authoring environments.}} @inproceedings{Wang.Park.ea_ViST_SIGMOD_2003, Address = {New York, NY, USA}, Author = {Wang, Haixun and Park, Sanghyun and Fan, Wei and Yu, Philip S.}, Booktitle = {Proc. of ACM SIGMOD Int. Conf. on Management of Data}, Conference-Abbr = {SIGMOD}, Doi = {http://doi.acm.org/10.1145/872757.872774}, Isbn = {1-58113-634-X}, Keywords = {XML indexing dynamic ViST query optimization labeling}, Location = {San Diego, California}, Pages = {110--121}, Pdf = {QueryEvaluation/XML/IndexingLabelling/Wang.Park.ea_ViST_SIGMOD_2003.pdf}, Publisher = {ACM Press}, Title = {{ViST: A Dynamic Index Method for Querying XML Data by Tree Structures}}, Url = {http://www.cs.ucr.edu/~tsotras/cs267/vist.pdf}, Year = {2003}, Abstract = {With the growing importance of XML in data exchange, much research has been done in providing flexible query facilities to extract data from structured XML documents. In this paper, we propose ViST, a novel index structure for searching XML documents. By representing both XML documents and XML queries in structure-encoded sequences, we show that querying XML data is equivalent to finding subsequence matches. Unlike index methods that disassemble a query into multiple sub-queries, and then join the results of these sub-queries to provide the final answers, ViST uses tree structures as the basic unit of query to avoid expensive join operations. Furthermore, ViST provides a unified index on both content and structure of the XML documents, hence it has a performance advantage over methods indexing either just content or structure. ViST supports dynamic index update, and it relies solely on B+ Trees without using any specialized data structures that are not well supported by DBMSs. Our experiments show that ViST is effective, scalable, and efficient in supporting structural queries.}} @inproceedings{Weigel.Meuss.ea_ContentStructureIDX_WebDB_2004, Address = {New York, NY, USA}, Author = {Weigel, Felix and Meuss, Holger and Schulz, Klaus U. and Bry, Fran\c{c}ois}, Booktitle = {Proc. Int. Workshop on the Web and Databases}, Conference-Abbr = {WebDB}, Doi = {http://doi.acm.org/10.1145/1017074.1017092}, Keywords = {XML indexing content index path index}, Location = {Paris, France}, Pages = {67--72}, Pdf = {QueryEvaluation/XML/IndexingLabelling/Weigel.Meuss.ea_ContentStructureIDX_WebDB_2004.pdf}, Publisher = {ACM Press}, Title = {{Content and Structure in Indexing and Ranking XML}}, Url = {http://portal.acm.org/citation.cfm?id=1017092}, Year = {2004}, Abstract = {Rooted in electronic publishing, XML is now widely used for modelling and storing structured text documents. Especially in the WWW, retrieval of XML documents is most useful in combination with a relevance-based ranking of the query result. Index structures with ranking support are therefore needed for fast access to relevant parts of large document collections. This paper proposes a classification scheme for both XML ranking models and index structures, allowing to determine which index suits which ranking model. An analysis reveals that ranking parameters related to both the content and structure of the data are poorly supported by most known XML indices. The IR-CADG index, owing to its tight integration of content and structure, supports various XML ranking models in a very efficient retrieval process. Experiments show that it outperforms separate content/structure indexing by more than two orders of magnitude for large corpora of several hundred MB.}} @inproceedings{Wu.Patel.ea_StructuralJoinOrder_ICDE_2003, Author = {Wu, Yuqing and Patel, Jignesh M. and Jagadish, H. V.}, Booktitle = {Proc. Int. Conf. on Data Engineering}, Conference-Abbr = {ICDE}, Keywords = {XML operators structural join query plan query optimization}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/StructuralJoins/Wu.Patel.ea_StructuralJoinOrder_ICDE_2003.pdf}, Title = {{Structural Join Order Selection for XML Query Optimization}}, Url = {http://csdl.computer.org/dl/proceedings/icde/2003/2071/00/20710443.pdf}, Year = {2003}, Abstract = {Structural join operations are central to evaluating queries against XML data, and are typically responsible for consuming a lion?s share of the query processing time. Thus, structural join order selection is at the heart of query optimization in an XML database, just as (value-based) join order selection is central to relational query optimization. In this paper, we introduce five algorithms for structural join order optimization for XML tree pattern matching and present an extensive experimental evaluation. Our experiments demonstrate that many relational rules of thumb are no longer appropriate: for instance, using dynamic programming style optimization is not efficient; limiting consideration to left-deep plans usually misses the best solution. Our experiments also show that a Dynamic Programming optimization with Pruning (DPP) algorithm can find the optimal solution, with low cost relative to the traditional Dynamic Programming (DP) algorithm; and an optimization technique that only considers Fully Pipelined (FP) plans can very quickly choose a plan that in most cases is close to optimal. Our recommendation is that DPP should be used in XML query optimizers where query execution time is expected to be significant, and that FP should be used where it is important to find a good (but not necessarily the best) plan quickly.}} @inproceedings{Yang.Fontoura.ea_VirtualCursorsXML_CIKM_2004, Address = {New York, NY, USA}, Author = {Yang, Beverly and Fontoura, Marcus and Shekita, Eugene and Rajagopalan, Sridhar and Beyer, Kevin}, Booktitle = {Proc. Conf. on Information and Knowledge Management}, Conference-Abbr = {CIKM}, Doi = {http://doi.acm.org/10.1145/1031171.1031271}, Isbn = {1-58113-874-1}, Keywords = {XML structural joins twig joins cursors query processing}, Location = {Washington, D.C., USA}, Pages = {523--532}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/StructuralJoins/Yang.Fontoura.ea_VirtualCursorsXML_CIKM_2004.pdf}, Publisher = {ACM Press}, Title = {{Virtual Cursors for XML Joins}}, Url = {http://portal.acm.org/citation.cfm?id=1031271}, Year = {2004}, Abstract = {Structural joins are a fundamental operation in XML query processing and a large body of work has focused on index-based algorithms for executing them. In this paper, we describe how two well-known index features -- path indices and ancestor information -- can be combined in a novel way to replace one or more of the physical index cursors in a structural join with virtual cursors. The position of a virtual cursor is derived from the path and ancestor information of a physical cursor. Implementation results are provided to show that, by eliminating index I/O, virtual cursors can improve the performance of structural joins by an order of magnitude or more.}} @inproceedings{Zhang.Ozsu.ea_NextOfKin_ICDE_2003, Author = {Zhang, Ning and Ozsu, M. Tamer and Kacholia, Varun}, Booktitle = {Proc. Int. Conf. on Data Engineering}, Conference-Abbr = {ICDE}, Keywords = {XML next-of-kin indexing storage}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/IndexingLabelling/Zhang.Ozsu.ea_NextOfKin_ICDE_2003.pdf}, Title = {{A Succinct Physical Storage Scheme for Single-Pass Evaluation of Next-of-Kin Path Queries in XML}}, Url = {http://db.uwaterloo.ca/~ddbms/publications/xml/icde04_storage_NoK.pdf}, Year = {2003}, Abstract = {Path expressions are ubiquitous in XML processing languages. Existing approaches evaluate a path expression by selecting nodes that satisfies the tag-name and value constraints and then joining them according to the structural constraints. In this paper, we propose a novel approach, next-of-kin (NoK) pattern matching, to speed up the nodeselection step, and to reduce the join size significantly in the second step. To efficiently perform NoK pattern matching, we also propose a succinct XML physical storage scheme that is adaptive to updates and streaming XML as well. Our performance results demonstrate that the proposed storage scheme and path evaluation algorithm is highly efficient and outperforms the other tested systems in most cases.}} @inproceedings{Zhang.Dimitrova.ea_RainbowMultiQs_SIGMOD_2003, Author = {Zhang, Xin and Dimitrova, Katica and Wang, Ling and Sayed, Maged El and Murphy, Brian and Pielech, Bradford and Mulchandani, Mukesh and Ding, Luping and Rundensteiner, Elke A.}, Booktitle = {Proc. ACM SIGMOD Int. Conf. on Management of Data}, Conference-Abbr = {SIGMOD}, Doi = {http://doi.acm.org/10.1145/872757.872861}, Isbn = {1-58113-634-X}, Keywords = {XML XQuery view-based query optimization evalution processing}, Location = {San Diego, California}, Pages = {671--671}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/Zhang.Dimitrova.ea_RainbowMultiQs_SIGMOD_2003.pdf}, Publisher = {ACM Press}, Title = {{Rainbow: multi-XQuery Optimization using Materialized XML Views}}, Url = {http://www.cs.wpi.edu/~lisading/docs/demo.pdf}, Year = {2003}, Abstract = {We present multiple XQuery optimization based on materialized XML view technology in the Rainbow system. In this demo we in particular show: (1) Rainbow?s support for defining and incrementally maintaining materialized XQuery views, (2) XQuery optimization by query rewriting to use materialized views, (3) Performing multiple query optimization by merging multiple XML queries (XATs) into one global access plan to decide upon materialization of intermediate results as views, and (4) Query processing of updates issued on XML views that wrap relational data by decomposing the updates into SQL update statements and consistency checks on the relational base data.}} @inproceedings{Zhang.Pielech.ea_HoneyIShrunkXAT_WIDM_2002, Author = {Zhang, Xin and Pielech, Bradford and Rundesnteiner, Elke A.}, Booktitle = {Proc. International Workshop on Web Information and Data Management}, Conference-Abbr = {WIDM}, Doi = {http://doi.acm.org/10.1145/584931.584936}, Isbn = {1-58113-593-9}, Keywords = {XML XQuery XAT algebraic optimization XML SQL rewriting optimization}, Location = {McLean, Virginia, USA}, Pages = {15--22}, Pdf = {QueryEvaluation/XML/AlgebraicOptimization/Zhang.Pielech.ea_HoneyIShrunkXAT_WIDM_2002.pdf}, Publisher = {ACM Press}, Title = {{Honey, I shrunk the XQuery!: an XML Algebra Optimization Approach}}, Url = {http://portal.acm.org/citation.cfm?id=584936}, Year = {2002}, Abstract = {A lot of work is being done in the database community on mapping of XML data into and out of relational database systems, specifically, the query processing over such data using XQuery. We discuss our solution, the XML Algebra Tree (XAT), as part of our larger XML management system called Rainbow.Rainbow uses XQuery to describe the loading and extracting of XML data into relational systems and also for the execution of queries against pre-defined XML views of that stored data. The XML algebra tree of the query against those views is merged with the queries that define the views to form a larger tree. Because the XML formatting operators are interleaved with the computation operators, this XAT must then be optimized before being translated into one or more SQL statements that can be executed on the database. SQL translation is composed of computation pushdown and SQL generation.The computation pushdown splits the tree into the XML-specific and SQL-doable operators, which is then going to be converted into SQL statements. However, the XAT after computation pushdown may contain unreferenced columns or unused operators. Leaving these operators in the tree will create unnecessarily large SQL statements and will slow down the overall execution.Our main contributions to XML query processing, outlined in this paper, are threefold. One, we describe an algebra based on XATs for modeling XQuery expressions. Two, we propose rewriting rules to optimize XQueries by XAT operator cancel out. Lastly, we show a cutting algorithm to remove unreferenced columns and operators from the trees. We have fully implemented the techniques discussed in this paper in the Rainbow system. A preliminary experimental study compares the performance of execution before and after operator cancel out and cutting.}} @inproceedings{Gottlob.Koch_MonadicQsTree_LICS_2002, Author = {Gottlob, Georg and Koch, Christoph}, Booktitle = {Proc. Annual IEEE Symposium on Logic in Computer Science}, Conference-Abbr = {LICS}, Date-Modified = {2006-02-01 17:38:32 +0100}, Group = {Matrix Method}, Isbn = {0-7695-1483-9}, Keywords = {XML monadic datalog query languages complexity semantics tree queries}, Pages = {189--202}, Pdf = {QueryEvaluation/XML/Comlexity/Gottlob.Koch_MonadicQsTree_LICS_2002.pdf}, Publisher = {IEEE Computer Society}, Title = {{Monadic Queries over Tree-Structured Data}}, Url = {http://www.dbai.tuwien.ac.at/proj/games/papers/lics2002.pdf}, Year = {2002}, Abstract = {Monadic query languages over trees currently receive considerable interest in the database community, as the problem of selecting nodes from a tree is the most basic and widespread database query problem in the context of XML. Partly a survey of recent work done by the authors and their group on logical query languages for this problem and their expressiveness, this paper provides a number of new results related to the complexity of such languages over so-called axis relations (such as ?child? or ?descendant?) which are motivated by their presence in the XPath standard or by their utility for data extraction (wrapping).}} @article{Gottlob.Koch.ea_EfficientXPath_TODS_2005, Author = {Gottlob, Georg and Koch, Christoph and Pichler, Reinhard}, Date-Modified = {2006-02-01 17:38:47 +0100}, Group = {Matrix Method}, Journal = {ACM Transactions on Database Systems}, Journal-Abbr = {TODS}, Keywords = {XML XPath efficient processing complexity}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/Comlexity/Gottlob.Koch.ea_EfficientXPath_TODS_2005.pdf}, Title = {{Efficient Algorithms for Processing XPath Queries}}, Url = {http://www.infosys.uni-sb.de/~koch/download/tods1.pdf}, Year = {2005}, Abstract = {Our experimental analysis of several popular XPath processors reveals a striking fact: Query evaluation in each of the systems requires time exponential in the size of queries in the worst case. We show that XPath can be processed much more e ciently, and propose main-memory algorithms for this problem with polynomial-time combined query evaluation complexity. Moreover, we show how the main ideas of our algorithm can be pro tably integrated into existing XPath processors. Finally, we present two fragments of XPath for which linear-time query processing algorithms exist and another fragment with linear-space/quadratic-time query processing.}} @inproceedings{Libkin_LogicTrees_ICALP2005, Author = {Libkin, Leonid}, Booktitle = {Proc. Intl. Colloquium on Automata, Languages and Programming}, Date-Added = {2006-02-01 17:23:06 +0100}, Date-Modified = {2006-02-01 17:31:59 +0100}, Group = {Matrix Method}, Pages = {35--50}, Title = {{Logics over Unranked Trees: An Overview}}, Url = {http://www.cs.toronto.edu/~libkin/papers/icalp05.ps.gz}, Year = {2005}, Abstract = {Labeled unranked trees are used as a model of XML documents, and logical languages for them have been studied actively over the past several years. Such logics have different purposes: some are better suited for extracting data, some for expressing navigational properties, and some make it easy to relate complex properties of trees to the existence of tree automata for those properties. Furthermore, logics differ significantly in their model-checking properties, their automata models, and their behavior on ordered and unordered trees. In this paper we present a survey of logics for unranked trees.}} @techreport{Furche_Syntax_DEL2006, Author = {Furche, Tim and Bry, Francois and Schaffert, Sebastian}, Date-Added = {2006-02-01 16:35:40 +0100}, Date-Modified = {2006-03-06 17:50:51 +0100}, Institution = {REWERSE}, Keywords = {XML Xcerpt syntax revision}, Number = {I4-D6}, Title = {{Initial Draft of a Language Syntax}}, Type = {Deliverable}, Url = {http://rewerse.net/publications.html#REWERSE-DEL-2006-I4-D6}, Year = {2006}} @article{Courcelle_InfiniteTrees_TCS1983, Author = {Courcelle, Bruno}, Date-Added = {2006-01-31 18:21:38 +0100}, Date-Modified = {2006-01-31 18:23:09 +0100}, Journal = {Theoretical Computer Science}, Keywords = {infinite trees data model references value identity}, Pages = {95--169}, Publisher = {Elsevier Science Publishers Ltd.}, Title = {{Fundamental Properties of Infinite Trees.}}, Volume = {25}, Year = {1983}, Abstract = {Infinite trees naturally arise in the formaliration and the c~udy of fhc \cm;lntic*, 01 prog-amming languages. This paper investigates some of their i:omninatorial and :iIgcbri\ic propei ties that are especially relevant to semantics. This paper is concerned in particular with regtilar and algchraic itlfinitc trees, rlor ln.ith rzg\lI;lr or algebraic s4f.s of infinite trees. For this reason moss of the propertics s~atcd in rhi$ IVOIX become trivial when restricted either to tinite trees or to infinite words. It present:, a synthesis of various aspects of infinite trees, invcstigatcd bc diIlt*ic*nt ,tuthor\ III differenr contlbxts and hopes to he a unifying step towards a theor! of infinite trct.4 tlliit coultl take place near the theory of formal languages and the combina:,:r::c of tk* free monoi,., }} @article{Codd_ExtendingRelationalModel_TODS1979, Address = {New York, NY, USA}, Author = {Codd, Edgar F.}, Date-Added = {2006-01-30 21:34:11 +0100}, Date-Modified = {2006-01-30 21:39:49 +0100}, Doi = {http://doi.acm.org/10.1145/320107.320109}, Issn = {0362-5915}, Journal = {ACM Transactions on Database Systems}, Keywords = {RDBMS model surrogates identity}, Number = {4}, Pages = {397--434}, Publisher = {ACM Press}, Title = {{Extending the Database Relational Model to Capture more Meaning}}, Url = {http://portal.acm.org/citation.cfm?id=320109}, Volume = {4}, Year = {1979}, Abstract = {During the last three or four years several investigators have been exploring ``semantic models'' for formatted databases. The intent is to capture (in a more or less formal way) more of the meaning of the data so that database design can become more systematic and the database system itself can behave more intelligently. Two major thrusts are clear. (1) the search for meaningful units that are as small as possible---atomic semantics; (2) the search for meaningful units that are larger than the usual n-ary relation---molecular semantics. In this paper we propose extensions to the relational model to support certain atomic and molecular semantics. These extensions represent a synthesis of many ideas from the published work in semantic modeling plus the introduction of new rules for insertion, update, and deletion, as well as new algebraic operators.}} @article{Kuper_LogicalDataModel_TODS1993, Address = {New York, NY, USA}, Author = {Kuper, Gabriel M. and Vardi, Moshe Y.}, Date-Added = {2006-01-30 10:00:50 +0100}, Date-Modified = {2006-01-30 10:01:41 +0100}, Doi = {http://doi.acm.org/10.1145/155271.155274}, Issn = {0362-5915}, Journal = {ACM Transactions on Database Systems}, Keywords = {object identity logic graphs}, Number = {3}, Pages = {379--413}, Publisher = {ACM Press}, Title = {{The Logical Data Model}}, Url = {http://portal.acm.org/citation.cfm?id=155274}, Volume = {18}, Year = {1993}, Abstract = {We propose an object-oriented data model that generalizes the relational, hierarchical, and network models. A database scheme in this model is a directed graph, whose leaves represent data and whose internal nodes represent connections among the data. Instances are constructed from objects, which have separate names and values. We define a logic for the model, and describe a nonprocedural query language that is based on the logic. We also describe an algebraic query language and show that it is equivalent to the logical language.}} @book{Fowler_Plato_HUP1977, Author = {Plato}, Date-Added = {2006-01-29 22:53:53 +0100}, Date-Modified = {2006-01-29 22:56:03 +0100}, Editor = {Harold N. Fowler (transl.)}, Publisher = {Harvard University Press}, Title = {{Plato in Twelve Volumes}}, Volume = {9}, Year = {1977}} @inproceedings{Grefen_MultiSetAlgebra_ICDE1994, Address = {Washington, DC, USA}, Author = {Grefen, Paul W. P. J. and de By, Rolf A.}, Booktitle = {Proc. Intl. Conf. on Data Engineering}, Date-Added = {2006-01-29 15:10:50 +0100}, Date-Modified = {2006-01-29 15:12:39 +0100}, Isbn = {0-8186-5400-7}, Keywords = {bags relational algebra optimization duplicates}, Pages = {80--88}, Publisher = {IEEE Computer Society}, Title = {{A Multi-Set Extended Relational Algebra---A Formal Approach to a Practical Issue}}, Year = {1994}, Abstract = {The relational data model is based on sets of tuples, i.e. it does not allow duplicate tuples in a relation. Many database languages and systems do require multi-set semantics though, either because of functional requirements or because of the high costs of duplicate removal in database operations. Several proposals have been presented that discuss multi-set semantics. As these proposals tend to be either rather practical, lacking the formal background, or rather formal, lacking the connection...}} @article{Ceri_Gottlob_Datalog_TKDE1989, Address = {Piscataway, NJ, USA}, Author = {Ceri, Stefano and Gottlob, Georg and Tanca, Letizia}, Date-Added = {2006-01-29 13:48:10 +0100}, Date-Modified = {2006-01-29 13:50:20 +0100}, Doi = {http://dx.doi.org/10.1109/69.43410}, Issn = {1041-4347}, Journal = {IEEE Transactions on Knowledge and Data Engineering}, Keywords = {Datalog Prolog logic programming}, Number = {1}, Pages = {146--166}, Publisher = {IEEE Educational Activities Department}, Title = {{What You Always Wanted to Know About Datalog (And Never Dared to Ask)}}, Url = {http://doi.ieeecomputersociety.org/10.1109/69.43410}, Volume = {1}, Year = {1989}, Abstract = {Datalog, a database query language based on the logic programming paradigm, is described. The syntax and semantics of Datalog and its use for querying a relational database are presented. Optimization methods for achieving efficient evaluations of Datalog queries are classified, and the most relevant methods are presented. Various improvements of Datalog currently under study are discussed, and what is still needed in order to extend Datalog's applicability to the solution of real-life problems is indicated.}} @article{Libkin_QLBagsAggregate_JCSS1997, Address = {Orlando, FL, USA}, Author = {Libkin, Leonid and Wong, Limsoon}, Date-Added = {2006-01-29 13:35:48 +0100}, Date-Modified = {2006-01-29 14:48:48 +0100}, Doi = {http://dx.doi.org/10.1006/jcss.1997.1523}, Issn = {0022-0000}, Journal = {Journal of Computer and System Sciences}, Keywords = {bags aggregation algebra query languages duplicates}, Number = {2}, Pages = {241--272}, Publisher = {Academic Press, Inc.}, Title = {{Query Languages for Bags and Aggregate Functions}}, Url = {http://citeseer.ist.psu.edu/libkin97query.html}, Volume = {55}, Year = {1997}, Abstract = {Theoretical foundations for querying databases based on bags are studied in this paper. We fully determine the strength of many polynomial-time bag operators relative to an ambient query language. Then we obtain BQL, a query language for bags, by picking the strongest combination of these operators. The relationship between the nested relational algebra and various fragments of BQL is investigated. The precise amount of extra power that BQL possesses over the nested relational algebra is...}} @inproceedings{Grumbach_AlgebraBags_PODS1993, Author = {Grumbach, St{\'e}phane and Milo, Tova}, Booktitle = {Proc. ACM Symposium on Principles of Database Systems}, Date-Added = {2006-01-29 04:58:42 +0100}, Date-Modified = {2006-01-29 05:00:50 +0100}, Keywords = {Bags algebra duplicate optimization}, Organization = {ACM Press}, Pages = {49--58}, Title = {{Towards Tractable Algebras for Bags}}, Url = {http://portal.acm.org/citation.cfm?id=153855}, Year = {1993}, Abstract = {Bags, i.e. sets with duplicates, are often used to implement relations in database systems. In this paper we study the expressive power of algebras for manipulating bags. The algebra we present is a simple extension of the nested relation algebra. Our aim is to investigate how the use of bags in the language extends its expressive power, and increases its complexity. We consider two main issues, namely (i) the relationship between the depth of bag nesting and the expressive power, and (ii) the relationship between the algebraic operations, and their complexity and expressive power. We show that the bag algebra is more expressive than the nested relation algebra (at all levels of nesting), and that the difference may be subtle. We establish a hierarchy based on the structure of algebra expressions. This hierarchy is shown to be highly related to the properties of the powerset operator.}} @inproceedings{Khoshafian_ObjectIdentity_OOPSLA1986, Address = {New York, NY, USA}, Author = {Khoshafian, Setrag N. and Copeland, George P.}, Booktitle = {Proc. Intl. Conf. on Object-oriented Programming Systems, Languages and Applications}, Date-Added = {2006-01-29 04:55:34 +0100}, Date-Modified = {2006-01-29 05:02:07 +0100}, Doi = {http://doi.acm.org/10.1145/28697.28739}, Isbn = {0-89791-204-7}, Keywords = {OODBMS object identity duplicates object sharing}, Location = {Portland, Oregon, United States}, Pages = {406--416}, Publisher = {ACM Press}, Title = {{Object Identity}}, Url = {http://portal.acm.org/citation.cfm?id=28739}, Year = {1986}, Abstract = {Identity is that property of an object which distinguishes each object from all others. Identity has been investigated almost independently in general-purpose programming languages and database languages. Its importance is growing as these two environments evolve and merge.We describe a continuum between weak and strong support of identity, and argue for the incorporation of the strong notion of identity at the conceptual level in languages for general purpose programming, database systems and their hybrids. We define a data model that can directly describe complex objects, and show that identity can easily be incorporated in it. Finally, we compare different implementation schemes for identity and argue that a surrogate-based implementation scheme is needed to support the strong notion of identity.}} @article{Abiteboul_ObjectIdentityQL_JACM1998, Address = {New York, NY, USA}, Author = {Abiteboul, Serge and Kanellakis, Paris C.}, Date-Added = {2006-01-29 04:53:52 +0100}, Date-Modified = {2006-01-30 03:58:55 +0100}, Doi = {http://doi.acm.org/10.1145/290179.290182}, Issn = {0004-5411}, Journal = {Journal of the ACM}, Keywords = {identity query languages object sharing cycles}, Number = {5}, Pages = {798--842}, Publisher = {ACM Press}, Title = {{Object Identity as a Query Language Primitive}}, Url = {http://portal.acm.org/citation.cfm?id=290182}, Volume = {45}, Year = {1998}, Abstract = {We demonstrate the power of object identities (oids) as a database query language primitive. We develop an object-based data model, whose structural part generalizes most of the known complex-object data models: cyclicity is allowed in both its schemas and instances. Our main contribution is the operational part of the data model, the query language IQL, which uses oids for three critical purposes: (1) to represent data-structures with sharing and cycles, (2) to manipulate sets, and (3) to express any computable database query. IQL can be type checked, can be evaluated bottom-up, and naturally generalizes most popular rule-based languages. The model can also be extended to incorporate type inheritance, without changes to IQL. Finally, we investigate an analogous value-based data model, whose structural part is founded on regular infinte trees and whose operational part is IQL.}} @inproceedings{Paparizos_TreeAlgebrasSetSequence_VLDB2005, Author = {Paparizos, Stelios and Jagadish, H. V.}, Booktitle = {Proc. Intl. Conf. on Very Large Data Bases}, Date-Added = {2006-01-29 04:49:55 +0100}, Date-Modified = {2006-01-29 04:52:41 +0100}, Isbn = {1-59593-154-6}, Keywords = {XML algebra order identity pattern matching query optimization}, Location = {Trondheim, Norway}, Pages = {349--360}, Publisher = {VLDB Endowment}, Title = {{Pattern Tree Algebras: Sets or Sequences?}}, Url = {http://portal.acm.org/citation.cfm?id=1083635}, Year = {2005}, Abstract = {XML and XQuery semantics are very sensitive to the order of the produced output. Although pattern-tree based algebraic approaches are becoming more and more popular for evaluating XML, there is no universally accepted technique which can guarantee both a correct output order and a choice of efficient alternative plans.We address the problem using hybrid collections of trees that can be either sets or sequences or something in between. Each such collection is coupled with an Ordering Specification that describes how the trees are sorted (full, partial or no order). This provides us with a formal basis for developing a query plan having parts that maintain no order and parts with partial or full order.It turns out that duplicate elimination introduces some of the same issues as order maintenance: it is expensive and a single collection type does not always provide all the flexibility required to optimize this properly. To solve this problem we associate with each hybrid collection a Duplicate Specification that describes the presence or absence of duplicate elements in it. We show how to extend an existing bulk tree algebra, TLC [12], to use Ordering and Duplicate specifications and produce correctly ordered results. We also suggest some optimizations enabled by the flexibility of our approach, and experimentally demonstrate the performance increase due to them.}} @incollection{Atkinson_ea_OOManifesto_MK1992, Address = {San Francisco, CA, USA}, Author = {Atkinson, Malcolm and DeWitt, David and Maier, David and Bancilhon, Fran{\c c}ois and Dittrich, Klaus and Zdonik, Stanley}, Booktitle = {{Building an Object-oriented Database System: The Story of O2}}, Chapter = {1}, Date-Added = {2006-01-29 04:44:06 +0100}, Date-Modified = {2006-01-29 04:49:53 +0100}, Editor = {Fran{\c c}ois Bancilhon and Claude Delobel and Paris Kanellakis}, Isbn = {1-55860-169-4}, Keywords = {OODBMS object identity principles}, Pages = {1--20}, Publisher = {Morgan Kaufmann Publishers Inc.}, Series = {Morgan Kaufmann Series In Data Management Systems}, Title = {{The Object-oriented Database System Manifesto}}, Url = {http://www.cs.cmu.edu/People/clamen/OODBMS/Manifesto/htManifesto/Manifesto.html}, Year = {1992}, Abstract = {This paper attempts to define an object-oriented database system. It describes the main features and characteristics that a system must have to qualify as an object-oriented database system. We have separated these characteristics into three groups: Mandatory, the ones the system must satisfy in order to be termed an object-oriented database system. These are complex objects, object identity, encapsulation, types or classes, inheritance, overriding combined with late binding, extensibility, computational completeness, persistence, secondary storage management, concurrency, recovery and an ad hoc query facility. Optional, the ones that can be added to make the system better, but which are not mandatory. These are multiple inheritance, type checking and inferencing, distribution, design transactions and versions. Open, the points where the designer can make a number of choices. These are the programming paradigm, the representation system, the type system, and uniformity. We have taken a position, not so much expecting it to be the final word as to erect a provisional landmark to orient further debate.}} @article{Stonebraker_ea_INGRES_TODS1976, Address = {New York, NY, USA}, Author = {Stonebraker, Michael and Held, Gerald and Wong, Eugene and Kreps, Peter}, Date-Added = {2006-01-29 00:53:42 +0100}, Date-Modified = {2006-01-29 00:56:22 +0100}, Doi = {http://doi.acm.org/10.1145/320473.320476}, Issn = {0362-5915}, Journal = {ACM Transactions on Database Systems}, Keywords = {RDBMS QUEL query language relational INGRES duplicates}, Number = {3}, Pages = {189--222}, Publisher = {ACM Press}, Title = {{The Design and Implementation of INGRES}}, Url = {http://portal.acm.org/citation.cfm?id=320476}, Volume = {1}, Year = {1976}, Abstract = {The currently operational (March 1976) version of the INGRES database management system is described. This multiuser system gives a relational view of data, supports two high level nonprocedural data sublanguages, and runs as a collection of user processes on top of the UNIX operating system for Digital Equipment Corporation PDP 11/40, 11/45, and 11/70 computers. Emphasis is on the design decisions and tradeoffs related to (1) structuring the system into processes, (2) embedding one command language in a general purpose programming language, (3) the algorithms implemented to process interactions, (4) the access methods implemented, (5) the concurrency and recovery control currently provided, and (6) the data structures used for system catalogs and the role of the database administrator. Also discussed are (1) support for integrity constraints (which is only partly operational), (2) the not yet supported features concerning views and protection, and (3) future plans concerning the system.}} @article{Astrahan_ea_SystemR_TODS1976, Address = {New York, NY, USA}, Author = {Astrahan, M. M. and Blasgen, M. W. and Chamberlin, D. D. and Eswaran, K. P. and Gray, J. N. and Griffiths, P. P. and King, W. F. and Lorie, R. A. and McJones, P. R. and Mehl, J. W. and Putzolu, G. R. and Traiger, I. L. and Wade, B. W. and Watson, V.}, Date-Added = {2006-01-29 00:51:24 +0100}, Date-Modified = {2006-01-29 00:55:45 +0100}, Doi = {http://doi.acm.org/10.1145/320455.320457}, Issn = {0362-5915}, Journal = {ACM Transactions on Database Systems}, Keywords = {RDBMS SQL SystemR query language duplicates}, Number = {2}, Pages = {97--137}, Publisher = {ACM Press}, Title = {{System R: Relational Approach to Database Management}}, Url = {http://portal.acm.org/citation.cfm?id=320457}, Volume = {1}, Year = {1976}, Abstract = {System R is a database management system which provides a high level relational data interface. The systems provides a high level of data independence by isolating the end user as much as possible from underlying storage structures. The system permits definition of a variety of relational views on common underlying data. Data control features are provided, including authorization, integrity assertions, triggered transactions, a logging and recovery subsystem, and facilities for maintaining data consistency in a shared-update environment. This paper contains a description of the overall architecture and design of the system. At the present time the system is being implemented and the design evaluated. We emphasize that System R is a vehicle for research in database architecture, and is not planned as a product.}} @inproceedings{Warren_ea_Prolog_AIPL1977, Author = {Warren, David H. D. and Pereira, Luis M. and Pereira, Fernando}, Booktitle = {Proc. Symposium on Artificial Intelligence and Programming Languages}, Date-Added = {2006-01-28 04:48:39 +0100}, Date-Modified = {2006-01-28 04:50:26 +0100}, Keywords = {Prolog programming language logic programming bags sets}, Pages = {109--115}, Title = {{Prolog - the Language and its Implementation compared with Lisp}}, Url = {http://portal.acm.org/citation.cfm?id=806939}, Year = {1977}, Abstract = {Prolog is a simple but powerful programming language founded on symbolic logic. The basic computational mechanism is a pattern matching process (``unification'') operating on general record structures (``terms'' of logic). We briefly review the language and compare it especially with pure Lisp. The remainder of the paper discusses techniques for implementing Prolog efficiently; in particular we describe how to compile the patterns involved in the matching process. These techniques are as incorporated in our DECsystem-10 Prolog compiler (written in Prolog). The code it generates is comparable in speed with that produced by existing DEC10 Lisp compilers. We argue that pattern matching is a better method for expressing operations on structured data than conventional selectors and constructors - both for the user and for the implementor.}} @article{Shipman_DAPLEX_TODS1981, Address = {New York, NY, USA}, Author = {Shipman, David W.}, Date-Added = {2006-01-28 04:42:24 +0100}, Date-Modified = {2006-01-28 04:43:49 +0100}, Doi = {http://doi.acm.org/10.1145/319540.319561}, Issn = {0362-5915}, Journal = {ACM Transactions on Database Systems}, Keywords = {query language DAPLEX multisets identity duplicates}, Number = {1}, Pages = {140--173}, Publisher = {ACM Press}, Title = {{The Functional Data Model and the Data Languages DAPLEX}}, Url = {http://portal.acm.org/citation.cfm?id=319561}, Volume = {6}, Year = {1981}, Abstract = {DAPLEX is a database language which incorporates: a formulation of data in terms of entities; a functional representation for both actual and virtual data relationships; a rich collection of language constructs for expressing entity selection criteria; a notion of subtype/supertype relationships among entity types. This paper presents and motivates the DAPLEX language and the underlying data model on which it is based.}} @inproceedings{Dayal_ea_RelationalAlgebraDuplicates_PODS1982, Address = {New York, NY, USA}, Author = {Dayal, Umeshwar and Goodman, Nathan and Katz, Randy H.}, Booktitle = {Proc. ACM Symposium on Principles of Database Systems}, Date-Added = {2006-01-28 04:38:16 +0100}, Date-Modified = {2006-01-28 04:44:38 +0100}, Doi = {http://doi.acm.org/10.1145/588111.588132}, Isbn = {0-89791-070-2}, Keywords = {identity multirelations multisets duplicates}, Location = {Los Angeles, California}, Pages = {117--123}, Publisher = {ACM Press}, Title = {{An Extended Relational Algebra with Control over Duplicate Elimination}}, Url = {http://portal.acm.org/citation.cfm?id=588132}, Year = {1982}, Abstract = {In the pure relational model, duplicate tuples are automatically eliminated. Some real world languages such as DAPLEX, however, give users control over duplicate elimination. This paper extends the relational model to include multiset relations, i.e., relations with duplicate tuples. It considers three formalisms for expressing queries in this model: extended relational algebra, tableaux, and DAPLEX. It shows that, as in the original algebra, the equivalence problem for conjunctive expressions in the extended algebra can be solved using tableaux, and is NP-complete. Finally, it demonstrates that the extended algebra and DAPLEX have essentially the same expressiveness relative to conjunctive expressions.}} @inproceedings{Klausner_Godman_Multirelations_VLDB1985, Author = {Klausner, Aviel and Goodman, Nathan}, Booktitle = {Proc. Intl. Conf. on Very Large Data Bases}, Date-Added = {2006-01-28 04:16:37 +0100}, Date-Modified = {2006-01-28 04:40:19 +0100}, Keywords = {identity duplicates RDBMS algebra relations multirelations}, Pages = {251--258}, Publisher = {Morgan Kaufmann}, Title = {{Multirelations --- Semantics and Languages}}, Url = {http://www.vldb.org/conf/1985/P251.PDF}, Volume = {11}, Year = {1985}, Abstract = {We argue that a multirelation (relation with duplicates) is not, a semantically independent data object, but rather it should be viewed as a sub- set of columns within a larger relation that has no duplicates. Consequently, at the level of the con- ceptual database, duplicates in base relations or in views are not allowed, nor are operations on mul- tirelations. Multirelations as query output can be specified by designating a subset of some relation's columns for output, while "hiding" the rest of the columns. Similarly, aggregate functions are applied to multirelations by applying them to a column within a relation. Our approach can be applied to extend any query language in a consistent way to have full multirelational expressiveness, and such an extension for the query language QUEL is detailed.}} @incollection{przymusinski-local-stratification, Author = {Przymusinsik, Teodor}, Booktitle = {Foundations of Deductive Databases and Logic Programming}, Chapter = 5, Editor = {Jack Minker}, Pages = {193--216}, Publisher = {Morgan Kaufmann}, Title = {{On the Declarative Semantics of Deductive Databases and Logic Programs}}, Year = 1988} @incollection{apt-stratification, Author = {Apt, Krzysztof and Blair, Howard and Walker, Adrian}, Booktitle = {Foundations of Deductive Databases and Logic Programming}, Chapter = 2, Editor = {Jack Minker}, Pages = {89--148}, Publisher = {Morgan Kaufmann}, Title = {{Towards a Theory of Deductive Knowledge}}, Year = 1988} @techreport{Clark_StylesheetPI_REC_1999, Author = {Clark, James}, Date-Added = {2005-11-13 20:29:51 +0100}, Date-Modified = {2005-11-13 20:30:45 +0100}, Institution = {W3C}, Title = {{Associating Style Sheets with XML Documents, Version 1.0}}, Type = {Recommendation}, Url = {http://www.w3.org/TR/xml-stylesheet/}, Year = {1999}, Abstract = {This document allows a style sheet to be associated with an XML document by including one or more processing instructions with a target of xml-stylesheet in the document's prolog.}} @techreport{Marsh.ea_XMLID_REC_2005, Author = {Marsh, Jonathan and Veillard, Daniel and Walsh, Norman}, Date-Added = {2005-11-13 20:16:58 +0100}, Date-Modified = {2005-11-13 20:18:35 +0100}, Institution = {W3C}, Keywords = {XML Identifier ID References Links Uniqueness}, Title = {{xml:id Version 1.0}}, Type = {Recommendation}, Url = {http://www.w3.org/TR/2005/REC-xml-id-20050909/}, Year = {2005}, Abstract = {This document defines the meaning of the attribute xml:id as an ID attribute in XML documents and defines processing of this attribute to identify IDs in the absence of validation, without fetching external resources, and without relying on an internal subset.}} @techreport{Clark_RelaxNC_2002, Author = {Clark, James}, Date-Added = {2005-11-06 02:56:35 +0100}, Date-Modified = {2005-11-06 02:57:06 +0100}, Institution = {OASIS}, Title = {{RELAX NG Compact Syntax}}, Type = {Committee Specification}, Url = {http://www.relaxng.org/compact-20021121.html}, Year = {2002}} @techreport{Clark.ea_RelaxNG_2001, Author = {Clark, James and Murata, Makoto}, Date-Added = {2005-11-06 02:53:54 +0100}, Date-Modified = {2005-11-06 02:55:37 +0100}, Institution = {OASIS}, Title = {{RELAX NG Specification}}, Type = {Committee Specification}, Url = {http://www.relaxng.org/spec-20011203.html}, Year = {2001}} @article{Naur.ea_ALGOL_CACM_1963, Author = {Backus, J. W. and Bauer, F. L. and Green, J. and Katz, C. and McCarthy, J. and Perlis, A. J. and Rutishauser, H. and Samelson, K. and Vauquois, B. and Wegstein, J. H. and van Wijngaarden, A. and Woodger, M.}, Date-Added = {2005-11-06 02:21:18 +0100}, Date-Modified = {2005-11-06 02:22:50 +0100}, Journal = {Communications of the ACM}, Number = {1}, Pages = {1--17}, Title = {{Revised Report on the Algorithm Language ALGOL 60}}, Volume = {6}, Year = {1963}} @inproceedings{Braz_RailroadDia_SIDOC_1990, Author = {Braz, Liza}, Booktitle = {Proc. Intl. Conf. on Systems Documentation}, Date-Added = {2005-11-06 01:48:34 +0100}, Date-Modified = {2005-11-06 01:49:52 +0100}, Pages = {23--27}, Publisher = {ACM Press}, Title = {{Visual Syntax Diagrams for Programming Language Statements}}, Year = {1990}} @manual{ISO_EBNF_1996, Date-Added = {2005-11-05 21:11:01 +0100}, Date-Modified = {2005-11-05 21:15:11 +0100}, Number = {14977:1996}, Organization = {ISO/IEC}, Title = {ISO/IEC 14977:1996, Syntactic Metalanguage -- Extended BNF}, Type = {International Standard}, Url = {http://standards.iso.org/ittf/PubliclyAvailableStandards/s026153_ISO_IEC_14977_1996(E).zip}, Year = {1996}} @techreport{Crocker.ea_ABNF_1997, Author = {Crocker, D. and Overell, P.}, Date-Added = {2005-11-05 21:07:00 +0100}, Date-Modified = {2005-11-05 21:08:02 +0100}, Institution = {IETF}, Number = {2234}, Title = {{Augmented BNF for Syntax Specifications: ABNF}}, Type = {Request for Comment (RFC)}, Url = {http://www.ietf.org/rfc/rfc2234.txt}, Year = {1997}} @article{Dovier.ea_RankBisimulation_ENTCS_2002, Author = {Dovier, Agostino and Gentilini, Raffaella and Piazza, Carla and Policriti, Alberto}, Bibsource = {DBLP, http://dblp.uni-trier.de}, Date-Added = {2005-10-27 15:21:02 +0200}, Date-Modified = {2005-10-27 15:22:05 +0200}, Ee = {http://www.elsevier.com/gej-ng/31/29/23/124/25/show/Products/notes/index.htt\#013}, Journal = {Electronic Notes on Theoretical Computer Science}, Title = {Rank-Based Symbolic Bisimulation (and Model Checking)}, Url = {http://wotan.liu.edu/docis/dbl/enitcs/2002_67__RSBMC.html#}, Volume = {67}, Year = {2002}} @article{Gentilini_BiSimulation_JAR_2003, Address = {Hingham, MA, USA}, Author = {Gentilini, R. and Piazza, C. and Policriti, A.}, Date-Added = {2005-10-27 15:15:42 +0200}, Date-Modified = {2005-10-27 15:16:26 +0200}, Doi = {http://dx.doi.org/10.1023/A:1027328830731}, Issn = {0168-7433}, Journal = {Journal of Automated Reasoning}, Number = {1}, Pages = {73--103}, Publisher = {Kluwer Academic Publishers}, Title = {{From Bisimulation to Simulation: Coarsest Partition Problems}}, Url = {http://www.dimi.uniud.it/~policrit/Papers/JAR_finale.pdf}, Volume = {31}, Year = {2003}} @article{Dovier.ea_AlgBisimulation_TCS_2004, Address = {Essex, UK}, Author = {Dovier, Agostino and Piazza, Carla and Policriti, Alberto}, Date-Added = {2005-10-27 15:05:30 +0200}, Date-Modified = {2005-10-27 15:10:24 +0200}, Doi = {http://dx.doi.org/10.1016/S0304-3975(03)00361-X}, Issn = {0304-3975}, Journal = {Theoretical Computer Science}, Number = {1-3}, Pages = {221--256}, Publisher = {Elsevier Science Publishers Ltd.}, Title = {{An efficient Algorithm for Computing Bisimulation Equivalence}}, Url = {http://www.dimi.uniud.it/~policrit/Papers/tcsb959.pdf}, Volume = {311}, Year = {2004}} @inproceedings{Milner_SimulationPrograms_IJCAI_1971, Author = {Milner, Robin}, Booktitle = {Proc. Intl. Joint Conf. on Artificial Intelligence}, Date-Added = {2005-10-27 14:49:18 +0200}, Date-Modified = {2005-10-27 14:50:37 +0200}, Pages = {481-489}, Title = {{An Algebraic Definition of Simulation Between Programs}}, Year = {1971}} @inproceedings{Henzinger.ea_Simulation_FOCS_1995, Address = {Washington, DC, USA}, Author = {Henzinger, M. R. and Henzinger, T. A. and Kopke, P. W.}, Booktitle = {Proc. Symp. on Foundations of Computer Science (FOCS)}, Date-Added = {2005-10-27 14:44:36 +0200}, Date-Modified = {2005-10-27 15:04:51 +0200}, Isbn = {0-8186-7183-1}, Pages = {453}, Publisher = {IEEE Computer Society}, Title = {{Computing Simulations on Finite and Infinite Graphs}}, Year = {1995}} @techreport{Schaffert.ea_DeclSemantics_D4_2005, Author = {Schaffert, Sebastian and Bry, Fran{\c c}ois and Furche, Tim}, Date-Added = {2005-10-23 17:11:23 +0200}, Date-Modified = {2006-03-06 17:49:01 +0100}, Institution = {REWERSE}, Keywords = {XML Xcerpt Unification Simulation Substitutions Declarative Semantics}, Number = {I4-D4}, Title = {{Initial Draft of a Possible Declarative Semantics for the Language}}, Type = {Deliverable}, Url = {http://rewerse.net/publications.html#REWERSE-DEL-2005-I4-D4}, Year = {2005}} @techreport{OMG_UML2_2005, Author = {{Object Management Group}}, Date-Added = {2005-10-15 23:22:03 +0200}, Date-Modified = {2005-10-15 23:23:34 +0200}, Institution = {Object Management Group}, Keywords = {UML modelling standard OMG}, Title = {{UML 2.0 Superstructure Specification}}, Type = {Specification}, Url = {http://www.omg.org/technology/documents/formal/uml.htm}, Year = {2005}, Abstract = {This UML 2.0: Superstructure is the second of two complementary specifications that represent a major revision to the Object Management Group's Unified Modeling Language (UML), for which the most current version is UML v1.4. The first specification, which serves as the architectural foundation for this specification, is the UML 2.0: Infrastructure. This UML 2.0: Superstructure defines the user level constructs required for UML 2.0. It is complemented by UML 2.0: Infrastructure which defines the foundational language constructs required for UML 2.0. The two complementary specifications constitute a complete specification for the UML 2.0 modeling language. }} @techreport{Marsh_XMLBase_2001, Author = {Marsh, Jonathan}, Date-Added = {2005-10-14 19:46:22 +0200}, Date-Modified = {2005-10-14 19:47:10 +0200}, Institution = {W3C}, Keywords = {XML URI base inclusion resolution}, Title = {{XML Base}}, Type = {Recommendation}, Url = {http://www.w3.org/TR/xmlbase/}, Year = {2001}} @techreport{Biron.ea_XMLSchemaDT_2004, Author = {Biron, Paul V. and Malhotra, Ashok}, Date-Added = {2005-10-14 19:31:57 +0200}, Date-Modified = {2005-10-14 19:33:06 +0200}, Institution = {W3C}, Keywords = {XML schema datatypes typing simple types}, Title = {{XML Schema Part 2: Datatypes Second Edition}}, Type = {Recommendation}, Url = {http://www.w3.org/TR/xmlschema-2/}, Year = {2004}, Abstract = {XML Schema: Datatypes is part 2 of the specification of the XML Schema language. It defines facilities for defining datatypes to be used in XML Schemas as well as other XML specifications. The datatype language, which is itself represented in XML 1.0, provides a superset of the capabilities found in XML 1.0 document type definitions (DTDs) for specifying datatypes on elements and attributes.}} @techreport{Fallside.ea_XMLSchemaPr_2004, Author = {Fallside, David C. and Walmsley, Priscilla}, Date-Added = {2005-10-14 19:26:24 +0200}, Date-Modified = {2005-10-14 19:30:58 +0200}, Institution = {W3C}, Keywords = {XML schema typing}, Title = {{XML Schema Part 0: Primer Second Edition}}, Type = {Recommendation}, Url = {http://www.w3.org/TR/xmlschema-0/}, Year = {2004}, Abstract = {XML Schema Part 0: Primer is a non-normative document intended to provide an easily readable description of the XML Schema facilities, and is oriented towards quickly understanding how to create schemas using the XML Schema language. XML Schema Part 1: Structures and XML Schema Part 2: Datatypes provide the complete normative description of the XML Schema language. This primer describes the language features through numerous examples which are complemented by extensive references to the normative texts.}} @techreport{Bry.ea_SimulationUnification_DEL_2005, Author = {Bry, Fran{\c c}ois and Furche, Tim and Schaffert, Sebastian and Schr{\"o}der, Andreas}, Date-Added = {2005-10-12 17:02:33 +0200}, Date-Modified = {2006-03-06 17:24:15 +0100}, Institution = {REWERSE}, Keywords = {XML Xcerpt Unification Simulation Unification Algebra Evaluation Operational Semantics}, Number = {I4-D5}, Title = {{Simulation Unification}}, Type = {Deliverable}, Url = {http://rewerse.net/publications.html#REWERSE-DEL-2005-I4-D5}, Year = {2005}} @techreport{Clark_XSLT_1999, Author = {Clark, James}, Date-Added = {2005-10-12 13:31:55 +0200}, Date-Modified = {2005-10-14 20:45:33 +0200}, Institution = {W3C}, Keywords = {XML XSLT standard recommendation}, Title = {{XSL Transformations, Version 1.0}}, Type = {Recommendation}, Url = {http://www.w3.org/TR/xslt}, Year = {1999}, Abstract = {This specification defines the syntax and semantics of XSLT, which is a language for transforming XML documents into other XML documents. XSLT is designed for use as part of XSL, which is a stylesheet language for XML. In addition to XSLT, XSL includes an XML vocabulary for specifying formatting. XSL specifies the styling of an XML document by using XSLT to describe how the document is transformed into another XML document that uses the formatting vocabulary. XSLT is also designed to be used independently of XSL. However, XSLT is not intended as a completely general-purpose XML transformation language. Rather it is designed primarily for the kinds of transformations that are needed when XSLT is used as part of XSL.}} @article{McHugh.ea_Lore_SIGR_1997, Address = {New York, NY, USA}, Author = {McHugh, Jason and Abiteboul, Serge and Goldman, Roy and Quass, Dallas and Widom, Jennifer}, Date-Added = {2005-10-12 13:22:50 +0200}, Date-Modified = {2005-10-12 13:30:07 +0200}, Doi = {http://doi.acm.org/10.1145/262762.262770}, Issn = {0163-5808}, Journal = {SIGMOD Record}, Local-Url = {file://localhost/Users/timfu/archive/research/bibliography/QueryEvaluation/XML/ProcessorsAndSystems/McHugh.ea_Lore_SIGR_1997.pdf}, Number = {3}, Pages = {54--66}, Publisher = {ACM Press}, Title = {{Lore: a database management system for semistructured data}}, Volume = {26}, Year = {1997}, Abstract = {Lore (for Lightweight Object Repository) is a DBMS designed specifically for managing semistructured information. Implementing Lore has required rethinking all aspects of a DBMS, including storage management, indexing, query processing and optimization, and user interfaces. This paper provides an overview of these aspects of the Lore system, as well as other novel features such as dynamic structural summaries and seamless access to data from external sources.}} @article{Abiteboul.Quass.ea_LorelQueryLanguage_JDL_1997, Author = {Abiteboul, Serge and Quass, Dallan and McHugh, Jason and Widom, Jennifer and Wienerm, Janet L.}, Date-Added = {2005-10-12 13:19:15 +0200}, Date-Modified = {2005-10-12 13:19:15 +0200}, Journal = {Intl. Journal on Digital Libraries}, Journal-Abbr = {JDL}, Keywords = {XML query languages Lorel language constructs semi-structured query}, Number = {1}, Pages = {68--88}, Pdf = {QueryEvaluation/XML/LanguageConstructs/PathVariables/Abiteboul.Quass.ea_LorelQueryLanguage_JDL_1997.pdf}, Title = {{The Lorel Query Language for Semistructured Data}}, Url = {http://www-db.stanford.edu/lore/pubs/lorel96.pdf}, Volume = {1}, Year = {1997}, Abstract = {We present the Lorel language, designed for querying semistructured data. Semistructured data is becoming more and more prevalent, e.g., in structured documents such as HTML and when performing simple integration of data from multiple sources. Traditional data models and query languages are inappropriate, since semistructured data often is irregular, some data is missing, similar concepts are represented using different types, heterogeneous sets are present, or object structure is not fully known. Lorel is a user-friendly language in the SQL/OQL style for querying such data effectively. For wide applicability, the simple object model underlying Lorel can be viewed as an extension of the ODMG data model and the Lorel language as an extension of OQL. The main novelties of the Lorel language are: (i) the extensive use of coercion to relieve the user from the strict typing of OQL, which is inappropriate for semistructured data; and (ii) powerful path expressions, which permit a flexible form of declarative navigational access and are particularly suitable when the details of the structure are not known to the user. Lorel also includes a declarative update language. Lorel is implemented as the query language of the Lore prototype database management system at Stanford. Information about Lore can be found at http://www-db.stanford.edu/lore. In addition to presenting the Lorel language in full, this paper briefly describes the Lore system and query processor. We also briefly discuss a second implementation of Lorel on top of a conventional object-oriented database management system, the O2 system.}} @techreport{IEEE_POSIX_2004, Author = {Group, The Austin}, Date-Added = {2005-09-29 01:07:30 +0200}, Date-Modified = {2005-09-29 01:13:13 +0200}, Institution = {IEEE, The Open Group}, Keywords = {IEEE POSIX open operating system}, Number = {1003.1}, Title = {IEEE Standard 1003.1, 2004 Edition (aka POSIX.1)}, Type = {IEEE Standard}, Url = {http://www.opengroup.org/onlinepubs/009695399/}, Year = {2001-2004}} @techreport{Duerst.Suignard_IRI_2005, Author = {Duerst, M. and Suignard, M.}, Date-Added = {2005-09-29 01:03:15 +0200}, Date-Modified = {2005-09-29 01:04:47 +0200}, Institution = {IEEE}, Keywords = {IRI URI identifiers RFC IEEE W3C}, Number = {3987}, Title = {{Internationalized Resource Identifiers (IRIs)}}, Type = {RFC (Request for Comments)}, Url = {http://www.faqs.org/rfcs/rfc3987.html}, Year = {2005}} @book{Gosling.Joy.ea_JavaSpec_2005, Author = {Gosling, James and Joy, Bill and Steele, Guy and Bracha, Gilad}, Date-Added = {2005-09-29 00:53:49 +0200}, Date-Modified = {2005-09-29 00:56:15 +0200}, Edition = {3rd}, Keywords = {Java JLS language specification grammar}, Publisher = {Addison-Wesley Professional}, Title = {Java Language Specification, Third Edition}, Url = {http://java.sun.com/docs/books/jls/}, Year = {2005}} @techreport{Bray.Hollander.ea_XMLNSRec_W3C_1999, Author = {Bray, Tim and Hollander, Dave and Layman, Andrew}, Date-Added = {2005-09-29 00:37:15 +0200}, Date-Modified = {2005-09-29 00:38:45 +0200}, Institution = {W3C}, Keywords = {XML W3C recommendation namespaces}, Owner = {Tim Furche}, Title = {{Namespaces in XML}}, Type = {Recommendation}, Url = {http://www.w3.org/TR/REC-xml-names/}, Urldate = {2005/09/31}, Year = {1999}, Abstract = {XML namespaces provide a simple method for qualifying element and attribute names used in Extensible Markup Language documents by associating them with namespaces identified by URI references.}} @techreport{Bray.Paoli.ea_XMLRec_W3C_2004, Author = {Bray, Tim and Paoli, Jean and Sperberg-McQueen, C. M. and Maler, Eve and Yergeau, Fran{\c c}ois}, Date-Added = {2005-09-29 00:30:06 +0200}, Date-Modified = {2005-09-29 00:41:34 +0200}, Institution = {W3C}, Keywords = {XML W3C recommendation}, Owner = {Tim Furche}, Title = {{Extensible Markup Language (XML) 1.0 (Third Edition)}}, Type = {Recommendation}, Url = {http://www.w3.org/TR/REC-xml/}, Urldate = {2005/09/31}, Year = {2004}, Abstract = {The Extensible Markup Language (XML) is a subset of SGML that is completely described in this document. Its goal is to enable generic SGML to be served, received, and processed on the Web in the way that is now possible with HTML. XML has been designed for ease of implementation and for interoperability with both SGML and HTML.}} @techreport{Alschuler.Dolin.ea_ClinicalDocumentArchitecture_TR_2000, Author = {Alschuler, Liora and Dolin, Robert H. and Boyer, Sandy and Beebe, Calvin}, Institution = {Health Level Seven (HL7)}, Owner = {Tim Furche}, Title = {{Clinical Document Architecture Framework}}, Year = {2000}} @techreport{Amer-YahiaBotev.XQuery-1.0-and-XPath.2005, Author = {Amer-Yahia, Sihem and Botev, Chavdar and Buxton, Stephen and Case, Pat and Doerre, Jochen and McBeath, Darin and Rys, Michael and Shanmugasundaram, Jayavel}, Date-Added = {2005-04-30 22:28:10 +0200}, Date-Modified = {2005-04-30 22:31:35 +0200}, Institution = {W3C}, Keywords = {XML XQuery full-text information retrieval}, Number = {Working Draft}, Title = {{XQuery 1.0 and XPath 2.0 Full-Text}}, Url = {http://www.w3.org/TR/xquery-full-text/}, Year = {2005}, Abstract = {This document defines the syntax and formal semantics of XQuery 1.0 and XPath 2.0 Full-Text which is a language that extends XQuery 1.0 [XQuery 1.0: An XML Query Language] and XPath 2.0 [XML Path Language (XPath) 2.0] with full-text search capabilities.}} @inproceedings{Amer-Yahia.Botev.ea_TeXQuery-Full-TextSearch_WWW_2004, Author = {Amer-Yahia, Sihem and Botev, Chavdar and Shanmugasundaram, Jayavel}, Booktitle = WWW, Conference-Abbr = {WWW}, Keywords = {XML IR query languages full-text information retrieval}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/InformationRetrieval/Languages/Amer-Yahia.Botev.ea_TeXQuery-Full-TextSearch_WWW_2004.pdf}, Title = {{TeXQuery: A Full-Text Search Extension to XQuery}}, Url = {http://www.research.att.com/~sihem/TeXQuery/TeXQuery.pdf}, Year = {2004}, Abstract = {One of the key benefits of XML is its ability to represent a mix of structured and unstructured (text) data. Although current XML query languages such as XPath and XQuery can express rich queries over structured data, they can only express very rudimentary queries over text data. We thus propose TeXQuery, which is a powerful full-text search extension to XQuery. TeXQuery provides a rich set of fully composable full-text search primitives, such as Boolean connectives, phrase matching, proximity distance, stemming and thesauri. TeXQuery also enables users to seamlessly query over both structured and text data by embedding TeXQuery primitives in XQuery, and vice versa. Finally, TeXQuery supports a flexible scoring construct that can be used to score query results based on full-text predicates. TeXQuery is one of the proposals submitted to the W3C Full-Text Task Force, whose charter is to extend XQuery with full-text search capabilities.}} @inproceedings{Amer-Yahia.Fernandez.ea_PIX-Exactand_SIGMOD_2003, Author = {Amer-Yahia, Sihem and Fernandez, Mary F. and Srivastava, Divesh and Xu, Yu}, Booktitle = SIGMOD, Conference-Abbr = {SIGMOD}, Keywords = {XML IR information retrieval query languages}, Owner = {Tim Furche}, Title = {{PIX: Exact and Approximate Phrase Matching in XML}}, Url = {http://www.research.att.com/~sihem/publications/demopixSIGMOD03.pdf}, Year = {2003}} @inproceedings{Amer-Yahia.Lakshmanan.ea_FleXPath:FlexibleStructure_SIGMOD_2004, Author = {Amer-Yahia, Sihem and Lakshmanan, Laks V. S. and Pandit, Shashank}, Booktitle = SIGMOD, Conference-Abbr = {SIGMOD}, Keywords = {XML IR query languages full-text information retrieval approximation structure}, Owner = {Tim Furche}, Title = {{FleXPath: Flexible Structure and Full-Text Querying for XML}}, Year = {2004}, Abstract = {Querying XML data is a well-explored topic with powerful database-style query languages such as XPath and XQuery set to become W3C standards. An equally compelling paradigm for querying XML documents is full-text search on textual content. In this paper, we study fundamental challenges that arise when we try to integrate these two querying paradigms.While keyword search is based on approximate matching, XPath has exact match semantics. We address this mismatch by considering queries on structure as a "template", and looking for answers that best match this template and the full-text search. To achieve this, we provide an elegant definition of relaxation on structure and define primitive operators to span the space of relaxations. Query answering is now based on ranking potential answers on structural and full-text search conditions. We set out certain desirable principles for ranking schemes and propose natural ranking schemes that adhere to these principles. We develop efficient algorithms for answering top-K queries and discuss results from a comprehensive set of experiments that demonstrate the utility and scalability of the proposed framework and algorithms.}} @article{Antoniou.Baldoni.ea_ReasoningMethodsPersonalization_AMCT_2004, Author = {Antoniou, Grigoris and Baldoni, Matteo and Baroglio, Cristina and Baumgartner, Robert and Bry, Fran{\c c}ois and Eiter, Thomas and Henze, Nicola and Herzog, Marcus and May, Wolfgang and Patti, Viviana and Schindlauer, Roman and Tompits, Hans and Schaffert, Sebastian}, Journal = {Annals of Mathematics, Computing \& Teleinformatics}, Journal-Abbr = {AMCT}, Keywords = {Semantic Web Personalization Reasoning REWERSE}, Number = {1}, Pages = {1--24}, Title = {{Reasoning Methods for Personalization on the Semantic Web}}, Url = {http://www.dbis.informatik.uni-goettingen.de/Publics/04/AMCT04.html}, Urldate = {2005/01/28}, Volume = {2}, Year = {2004}, Abstract = {The Semantic Web vision of a next generation Web, in which machines are enabled to understand the meaning of information in order to better interoperate and better support humans in carrying out their tasks, is very appealing and fosters the imagination of smarter applications that can retrieve, process and present information in enhanced ways. In this vision, a particular attention should be devoted to personalization: By bringing the user's needs into the center of interaction processes, personalized Web systems overcome the one-size-fits-all paradigm and provide individually optimized access to Web data and information. In this paper, we provide an overview of recent trends for establishing personalization on the Semantic Web: Based on a discussion on reasoning with rule- and query languages for the Semantic Web, we outline an architecture for service-based personalization, and show results in personalizing Web applications.}} @techreport{Apparao.Byrne.ea_DocumentObjectModel_TR_1998, Author = {Apparao, Vidur and Byrne, Steve and Champion, Mike and Isaacs, Scott and Jacobs, Ian and Hors, Arnaud Le and Nicol, Gavin and Robie, Jonathan and Sutor, Robert and Wilson, Chris and Wood, Lauren}, Institution = {W3C}, Keywords = {XML DOM W3C data model document object model}, Owner = {Tim Furche}, Title = {{Document Object Model (DOM) Level 1 Specification}}, Type = {Recommendation}, Url = {http://www.w3.org/TR/REC-DOM-Level-1/}, Urldate = {2005/01/31}, Year = {1998}, Abstract = {This specification defines the Document Object Model Level 1, a platform- and language-neutral interface that allows programs and scripts to dynamically access and update the content, structure and style of documents. The Document Object Model provides a standard set of objects for representing HTML and XML documents, a standard model of how these objects can be combined, and a standard interface for accessing and manipulating them. Vendors can support the DOM as an interface to their proprietary data structures and APIs, and content authors can write to the standard DOM interfaces rather than product-specific APIs, thus increasing interoperability on the Web. The goal of the DOM specification is to define a programmatic interface for XML and HTML. The DOM Level 1 specification is separated into two parts: Core and HTML. The Core DOM Level 1 section provides a low-level set of fundamental interfaces that can represent any structured document, as well as defining extended interfaces for representing an XML document. These extended XML interfaces need not be implemented by a DOM implementation that only provides access to HTML documents; all of the fundamental interfaces in the Core section must be implemented. A compliant DOM implementation that implements the extended XML interfaces is required to also implement the fundamental Core interfaces, but not the HTML interfaces. The HTML Level 1 section provides additional, higher-level interfaces that are used with the fundamental interfaces defined in the Core Level 1 section to provide a more convenient view of an HTML document. A compliant implementation of the HTML DOM implements all of the fundamental Core interfaces as well as the HTML interfaces.}} @inproceedings{Augurusa.Braga.ea_DesignandImplementation_SAC_2003, Author = {Augurusa, Enrico and Braga, Daniele and Campi, Alessandro and Ceri, Stefano}, Booktitle = SAC, Conference-Abbr = {SAC}, Doi = {http://doi.acm.org/10.1145/952532.952759}, Isbn = {1-58113-624-2}, Keywords = {XML XQuery visual query language XQBE query-by-example}, Location = {Melbourne, Florida}, Pages = {1163--1167}, Pdf = {QueryEvaluation/XML/XQuery/Augurusa.Braga.ea_DesignandImplementation_SAC_2003.pdf}, Publisher = {ACM Press}, Title = {{Design and Implementation of a Graphical Interface to XQuery}}, Url = {http://dbgroup.elet.polimi.it/xquery/papers/XQBE-SAC03.pdf}, Year = {2003}, Abstract = {As the use of XML is rapidly growing, a growing number of users without programming skills will need to query XML data. Although designed to be easily understood by humans, XQuery, the XML standard query language, has the typical syntax of programming languages, which most users dislike. In this paper we describe a graphical language (XQBE) inspired by "Query By Example" (QBE), a popular relational query language used by MS Access. XQBE covers a significant subset of XQuery and is supported by a prototype enabling the formulation of queries on a graphical interface and their translation into XQuery, thus providing non-trivial querying capabilities to a wide spectrum of users. Simple queries are easily represented in XQBE, but many "complex" queries allow as well for an intuitive graphical representation.}} @inproceedings{Assmann.Henriksson.ea_Comp_PPSWR_2005, Author = {A{\ss}mann, Uwe and Henriksson, Jakob and Maluszynski, Jan}, Booktitle = {Proc. Workshop on Principles and Practice of Semantic Web Reasoning}, Conference-Abbr = {PPSWR}, Keywords = {composition Semantic Web ontologies rule languages I3}, Owner = {Tim Furche}, Pdf = {SemanticWeb/Ontologies/Assmann.Henriksson.ea_Comp_PPSWR_2005.pdf}, Title = {{A Hybrid Technique for Composition of Rules and Ontologies for Semantic Web Reasoning}}, Year = {2005}, Abstract = {Previous approaches towards combining rule languages with Description-Logic-based ontologies require specialized reasoners for each specific combination. We outline a general technique for combining various classes of rule languages with various constraint languages including but not restricted to Description-Logic-based ontologies. The combination is such that existing reasoners, considered as software components, can be re-used for reasoning in the combined language, if they support external calls to rules or functions. We specifically formulate the approach as a software component model as studied in software engineering. We illustrate the technique by showing how a subset of SWRL can be implemented by combination of a Datalog interpreter and OWL reasoner.}} @inproceedings{Backofen.Badea.ea_PosterTowardssemantic_SocBIN_2004, Author = {Backofen, Rolf and Badea, Mike and Barahona, Pedro and Badea, Liviu and Bry, Fran{\c c}ois and Dawelbait, Gihan and Doms, Andreas and Fages, Fran{\c c}ois and Goble, Carole and Henschel, Andreas and Hotaran, Anca and Huang, Bingding and Krippahl, Ludwig and Lambrix, Patrick and Nutt, Werner and Schroeder, Michael and Soliman, Sylvain and Will, Sebastian}, Booktitle = {Prof. Bioinformatics}, Conference-Abbr = {SocBIN}, Keywords = {REWERSE Bioinformatics Semantic Web}, Organization = {SocBIN - Society for Bioinformatics in the Nordic countries}, Title = {{Poster: Towards a semantic web for bioinformatics}}, Url = {http://rewerse.net/publications.html#REWERSE-RP-2004-26}, Year = {2004}} @techreport{Badea.Bry.ea_DevelopmentofUse_TR_2005, Author = {Badea, Liviu and Bry, Fran{\c c}ois and Doms, Andreas and Furche, Tim and Hoffmann, Jan and Schaffert, Sebastian and Schroeder, Michael}, Date-Modified = {2005-05-01 23:00:30 +0200}, Institution = {REWERSE}, Keywords = {REWERSE Query languages Use Cases Versatility Deliverable}, Number = {I4-D3}, Owner = {Tim Furche}, Title = {{Development of Use Cases, Part II: Usage Scenarios for a Versatile Web Query Language}}, Type = {Deliverable}, Year = {2005}} @inproceedings{Badea.Tilivea.ea_SemanticWebReasoning_PPSWR_2004, Author = {Badea, Liviu and Tilivea, Doina and Hotaran, Anca}, Booktitle = PPSWR, Conference-Abbr = {PPSWR}, Keywords = {Web Semantic Web REWERSE}, Organization = {REWERSE}, Pdf = {SemanticWeb/REWERSE/Badea.Tilivea.ea_SemanticWebReasoning_PPSWR_2004.pdf}, Publisher = {Springer-Verlag}, Series = {LNCS}, Title = {{Semantic Web Reasoning for Ontology-Based Integration of Resources}}, Url = {http://www.ai.ici.ro/papers/ppswr04f.pdf}, Urldate = {2004/11/11}, Volume = {3208}, Year = {2004}, Abstract = {The Semantic Web should enhance the current World Wide Web with reasoning capabilities for enabling automated processing of possibly distributed information. In this paper we describe an architecture for Semantic Web reasoning and query answering in a very general setting involving several heterogeneous information sources, as well as domain ontologies needed for offering a uniform and source-independent view on the data. Since querying a Web source is very costly in terms of response time, we focus mainly on the query planner of such a system, as it may allow avoiding the access to queryirrelevant sources or combinations of sources based on knowledge about the domain and the sources.}} @inproceedings{Bae.Bailey_CodeXapproachdebugging_WISE_2003, Author = {Bae, Eric and Bailey, James}, Booktitle = {Web Information Systems Engineering, 2003. WISE 2003. Proceedings of the Fourth International Conference on}, Conference-Abbr = {WISE}, Keywords = {XML XSLT debugging query languages}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/XSLT/Bae.Bailey_CodeXapproachdebugging_WISE_2003.pdf}, Title = {{CodeX: an approach for debugging XSLT transformations}}, Url = {http://www.cs.mu.oz.au/~jbailey/papers/wise.ps}, Year = {2003}, Abstract = {XML is now a dominant standard for storing and exchanging information. One very important activity is the transformation of XML documents into other formats, via the transformation language XSLT. XSLT provides a powerful way to perform document conversion and exchange, avoiding reliance on application specific solutions. However, XSLT is a complex language and the current level of support for debugging tools is poor. Many tools that do exist are mainly an extension of conventional techniques for imperative programs and not well-suited to the task. In this paper, we present CodeX, a debugger for XSLT and propose three debugging techniques which are particularly suited to the language. We aim to offer XSLT users a tool which is beneficial in finding errors, as well as facilitating a better understanding of the XML transformation process.}} @inproceedings{Bailey_TransformationandReaction_ADC_2005, Author = {Bailey, James}, Booktitle = {Proc. Australasian Database Conference}, Conference-Abbr = {ADC}, Keywords = {XML XSLT transformation reactivity research issues}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/XSLT/Bailey_TransformationandReaction_ADC_2005.pdf}, Title = {{Transformation and Reaction Rules for Data on the Web}}, Url = {http://crpit.com/confpapers/CRPITV39Bailey.pdf}, Year = {2005}, Abstract = {The transformation and manipulation of XML is an increasingly important research topic. This paper examines a number of issues with regard to languages for transforming and reacting to changes on XML data. On the transformation side, we focus on XSLT, a powerful language for converting XML data into other formats. We look at analysis and optimisation issues for XSLT, as well as support for debugging and automatic generation. On the reactivity side, we focus on an event-condition-action rule approach, which is a natural candidate for the support of reactive functionality on XML repositories.}} @incollection{BaileyBry.Web-and-Semantic-Web.2005, Author = {Bailey, James and Bry, Fran{\c c}ois and Furche, Tim and Schaffert, Sebastian}, Booktitle = {Reasoning Web Summer School 2005}, Date-Added = {2005-04-20 13:38:00 +0200}, Date-Modified = {2006-03-06 17:46:19 +0100}, Editor = {Jan Maluszinsky and Norbert Eisinger}, Number = {3564}, Publisher = {Springer-Verlag}, Series = {LNCS}, Title = {{Web and Semantic Web Query Languages: A Survey}}, Url = {http://www.pms.ifi.lmu.de/publikationen#PMS-FB-2005-14}, Year = {2005}, Abstract = {A number of techniques have been developed to facilitate powerful data retrieval on the Web and Semantic Web. Three categories of Web query languages can be distinguished, according to the format of the data they can retrieve: XML, RDF and Topic Maps. This article introduces the spectrum of languages falling into these categories and summarises their salient aspects. The languages are introduced using common sample data and query types. Key aspects of the query languages considered are stressed in a conclusion. }} @inproceedings{Bartlett.Cook_XMLSecurityusing_SS_2003, Author = {Bartlett, Robert G. and Cook, Malcolm W.}, Booktitle = {Proc. Intl. Conf. on System Sciences}, Conference-Abbr = {SS}, Keywords = {XML XSLT cryptography security query languages}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/XSLT/Bartlett.Cook_XMLSecurityusing_SS_2003.pdf}, Title = {{XML Security using XSLT}}, Url = {http://www.cit.uws.edu.au/research/reports/paper/paper02/robert-15-02.pdf}, Year = {2003}, Abstract = {The eXtensible Markup Language (XML) is regarded generally as having promise of becoming established as the general purpose framework for enabling transfer of data amongst heterogeneous environments. It is of interest therefore to analyse how suitable it may be once details of applications requirements and constraints are taken into account. One important requirement is for the security of documents in transit. Closely associated with XML is the eXtensible Stylesheet Language (XSL), whose document transformation component (XSLT) may well have sufficient functionality to perform all reasonable cryptographic transformations to deliver a desired level of document security. We examine this question by describing a real world XML application whose security requirements are more complex than for a simple document transfer between just two parties; proposing a document transfer architecture into which XSLT can be plugged-in; and identifying those features of XSLT which must be applied to meet the application requirements. We conclude that XSLT is only just adequate in the proposed scenario; and then only by making use of its " extension functions " capability.}} @inproceedings{Baumgartner.Gottlob.ea_AnnotatingLegacyWeb_ISWC_2004, Author = {Baumgartner, Robert and Gottlob, Georg and Herzog, Marcus and Slany, Wolfgang}, Booktitle = ISWC, Conference-Abbr = {ISWC}, Keywords = {Lixto Extraction Legacy Web XML Wrapper REWERSE}, Owner = {Tim Furche}, Pdf = {SemanticWeb/Extraction/Baumgartner.Gottlob.ea_AnnotatingLegacyWeb_ISWC_2004.pdf}, Title = {{Annotating the Legacy Web with Lixto}}, Url = {http://iswc2004.semanticweb.org/demos/21/paper.pdf}, Urldate = {2005/01/28}, Year = {2004}, Abstract = {The Semantic Web is still a vision. The unstructured Web of today contains millions of documents which cannot be queried and where layout and structure are heavily mixed. Moreover, they are not annotated at all. There is a huge gap between Web information and the qualified, structured data as required in corporate information systems. According to the vision of the Semantic Web, all information available on the Web will be suitably structured, annotated, and qualified in the future. However, until this goal is reached, and also, towards a faster achievement of this goal, relevant data can be (semi-)automatically extracted from HTML documents and automatically translated into a structured format, e.g., XML. A program that automatically extracts data and transforms it into another format (markups the content with semantic information) is called a wrapper. Intelligent content extraction provides the foundation for automatic generation of semantic markup. Various approaches to automatic content extraction have been proposed, ranging from machine learning techniques to pattern recognition techniques. However, these approaches in general fail to produce useful results due to the complexity of Web pages. Other approaches suggest the manual editing of script files that wrap the relevant data from Web pages into more structured formats. Such processes are time-consuming, hard to understand for non-technical wrapper designers, and script files are not easy to maintain. We propose another approach - a supervised and visual definition of content extraction. Based on interactively identifying and extracting relevant parts of HTML documents and translating content to XML format, we designed and implemented the efficient wrapper generation tool Lixto Visual Wrapper [2] which is well-suited for building HTML to XML wrappers. Such a wrappeapplied to continually extract relevant information from this class of Web pages.}} @inproceedings{Bayardo.Gruhl.ea_EvaluationofBinary_WWW_2004, Author = {Bayardo, Roberto J. and Gruhl, Daniel and Josifovski, Vanja and Myllymaki, Jussi}, Booktitle = WWW, Conference-Abbr = {WWW}, Doi = {http://doi.acm.org/10.1145/988672.988719}, Isbn = {1-58113-844-X}, Keywords = {XML XQuery stream binary encoding}, Location = {New York, NY, USA}, Pages = {345--354}, Pdf = {QueryEvaluation/XML/XQuery/Bayardo.Gruhl.ea_EvaluationofBinary_WWW_2004.pdf}, Publisher = {ACM Press}, Title = {{An Evaluation of Binary XML Encoding Optimizations for fast Stream based XML Processing}}, Url = {http://www.www2004.org/proceedings/docs/1p345.pdf}, Year = {2004}, Abstract = {This paper provides an objective evaluation of the performance impacts of binary XML encodings, using a fast stream-based XQuery processor as our representative application. Instead of proposing one binary format and comparing it against standard XML parsers, we investigate the individual effects of several binary encoding techniques that are shared by many proposals. Our goal is to provide a deeper understanding of the performance impacts of binary XML encodings in order to clarify the ongoing and often contentious debate over their merits, particularly in the domain of high performance XML stream processing.}} @inproceedings{Berger.Bry.ea_XcerptandvisXcerpt_ISWC_2004, Author = {Berger, Sacha and Bry, Fran{\c c}ois and Bolzer, Oliver and Furche, Tim and Schaffert, Sebastian and Wieser, Christoph}, Booktitle = ISWC, Conference-Abbr = {ISWC}, Keywords = {Semantic Web XML RDF Visualization Xcerpt Demo REWERSE visXcerpt}, Pdf = {SemanticWeb/Xcerpt/Visualization/Berger.Bry.ea_XcerptandvisXcerpt_ISWC_2004.pdf}, Title = {{Xcerpt and visXcerpt: Twin Query Languages for the Semantic Web}}, Url = {http://www.pms.ifi.lmu.de/publikationen/#PMS-FB-2004-23}, Urldate = {2004/11/11}, Year = {2004}, Abstract = {Query and transformation languages such as XPath, XQuery and XSLT have evolved to standard development tools for Web applications. Arguably those languages are not fully suited for Semantic Web applications. The query and transformation languages Xcerpt and visXcerpt have been conceived with both standard Web and Semantic Web applications in mind. They are twin languages both based on the same paradigms and principles. Xcerpt realizes these paradigms and principles textually, visXcerpt visually. A mixed standard Web and Semantic Web application scenario implemented in Xcerpt and visXcerpt is presented. Xcerpt and visXcerpt are ongoing research projects; prototypic implementations of the languages are available.}} @inproceedings{Berger.Bry.ea_ReasoningonWeb_EWIMT_2004, Author = {Berger, Sacha and Bry, Fran{\c c}ois and Lorenz, Bernhard and Ohlbach, Hans J{\"u}rgen and P?tr{\^a}njan, Paula-Lavinia and Schaffert, Sebastian and Schwertel, Uta and Spranger, Stephanie}, Booktitle = {Proc. European Workshop on the Integration of Knowledge, Semantics and Digital Media Technology}, Conference-Abbr = {EWIMT}, Keywords = {REWERSE Reasoning Semantic Web Query Languages Reactivity Temporal Reasoning}, Organization = {IEEE}, Pages = {157--164}, Pdf = {SemanticWeb/REWERSE/Berger.Bry.ea_ReasoningonWeb_EWIMT_2004.pdf}, Title = {{Reasoning on the Web: Language Prototypes and Perspectives}}, Url = {http://rewerse.net/publications.html#REWERSE-RP-2004-39}, Year = {2004}, Abstract = {Reasoning on the Web is gaining in importance because of emerging Web applications such as context-adaptive Web systems (e.g. eLearning, rec ommender, personalised (multi-)media, and mobile information systems), Web service retrieval and composition, and Semantic Web applications of all kinds. A central issue is combining automated reasoning methods with Web languages, especially with Web query, schema, and update languages. This article reports on prototypes of various kinds combining different forms of reasoning with Web languages. The languages presented here have been conceived for both, convention al Web and Semantic Web data, assuming that future Web applications will require to freely combine data of both kinds.}} @inproceedings{Berger.Bry.ea_XcerptetvisXcerpt_JFPLC_2004, Author = {Berger, Sacha and Bry, Fran{\c c}ois and Schaffert, Sebastian}, Booktitle = {Proc. Journ{\'e}es Francophones de Programmation en Logique et Programmation par Contraintes}, Conference-Abbr = {JFPLC}, Keywords = {REWERSE Query Languages Xcerpt visXcerpt Visualization}, Organization = {INRIA}, Pdf = {SemanticWeb/REWERSE/Berger.Bry.ea_XcerptetvisXcerpt_JFPLC_2004.pdf}, Title = {{Xcerpt et visXcerpt : Langages d{\'e}ductifs d?interrogation du Web}}, Url = {http://rewerse.net/publications.html#REWERSE-RP-2004-13}, Year = {2004}, Abstract = {Web Query languages like XPath, XQuery and XSLT are widely accepted tools for the development of Web applications today. This article presents and motivates two new and experimental query languages for the Web: Xcerpt and visXcerpt (see http://xcerpt.org). Both languages are based on the same principles. They are deductive languages, which is one of their central aspects: they use a sort of unification similar to the unification used in logic programming and deduction systems, as well as an inference mechanism similar to that of logic programming and to SQL views in databases. visXcerpt is a visual query language which provides a visual realization of Xcerpt's textual constructs. Xcerpt's and visXcerpt's main goal is to ease the development of applications for the Semantic Web applications. This article introduces the essential aspects of Xcerpt and visXcerpt.}} @inproceedings{Berger.Bry.ea_XcerptundvisXcerpt_GDB_2004, Author = {Berger, Sacha and Bry, Fran{\c c}ois and Schaffert, Sebastian}, Booktitle = {Proc. Workshop Grundlagen von Datenbanken}, Conference-Abbr = {GDB}, Keywords = {REWERSE visXcerpt Xcerpt Query Languages Semantic Web}, Organization = {GI}, Pdf = {SemanticWeb/REWERSE/Berger.Bry.ea_XcerptundvisXcerpt_GDB_2004.pdf}, Title = {{Xcerpt und visXcerpt: deduktive Anfragesprachen f{\"u}r das Web}}, Url = {http://rewerse.net/publications.html#REWERSE-RP-2004-66}, Year = {2004}, Abstract = {Anfragesprachen f{\"u}r XML-Daten sind heutzutage wesentliche Werkzeuge in der Entwicklung von Webanwendungen. Die am weitesten verbreiteten Sprachen sind XQuery und XSLT, die beide auf der pfadbasierten Selektionssprache XPath aufbauen. Dieser Vortrag gibt einen Einblick in eine neue Anfragesprache namens Xcerpt, die statt des pfadbasierten Ansatzes Anfragepattern verwendet, welche eine deklarativere Spezifikation von Anfragen erlauben. Xcerpt ist ausserdem eine deduktive, regelbasierte Sprache, die auch die Verkn{\"u}pfung von mehreren Regeln (Chaining) und Rekursion erm{\"o}glicht. Eine Xcerpt-Regel kann damit auch als Abstraktion der Ausgangsdaten verstanden werden, hnlich zu Views in relationalen Datenbanken.Auf Xcerpt aufbauend wird ausserdem die visuelle Anfragesprache visXcerpt vorgestellt. Aufgrund des patternbasierten Ansatzes von Xcerpt k{\"o}nnen in visXcerpt Anfragen auf einfache Weise visuell dargestellt und bearbeitet werden.Das Ziel beider Anfragesprachen ist es, die Entwicklung von Anwendungen insbesondere f{\"u}r das "Semantic Web" zu vereinfachen:Anfnger k{\"o}nnen mit Hilfe von visXcerpt Anfragen schnell und intuitiv formulieren und Fortgeschrittenen hilft die Deklarativitt von Xcerpt bei der Gliederung komplexer Programme.}} @inproceedings{Berger.Bry.ea_VisualLanguageWeb_PPSWR_2003, Author = {Berger, Sacha and Bry, Fran{\c c}ois and Schaffert, Sebastian}, Booktitle = PPSWR, Conference-Abbr = {PPSWR}, Keywords = {Xcerpt visXcerpt Demo Visualization Query Languages}, Pdf = {SemanticWeb/Xcerpt/Visualization/Berger.Bry.ea_VisualLanguageWeb_PPSWR_2003.pdf}, Publisher = {Springer-Verlag}, Series = {LNCS}, Title = {{A Visual Language for Web Querying and Reasoning}}, Url = {http://www.pms.ifi.lmu.de/publikationen/#PMS-FB-2003-6}, Volume = {2901}, Year = {2003}, Abstract = {As XML is increasingly being used to represent information on the Web, query and reasoning languages for such data are needed. This article argues that in contrast to the navigational approach taken in particular by XPath and XQuery, a positional approach as used in the language Xcerpt is better suited for a straightforward visual representation. The constructs of the pattern- and rule-based query language Xcerpt are introduced and it is shown how the visual representation visXcerpt renders these constructs to form a visual query language for XML.}} @inproceedings{Berger.Bry.ea_XcerptandvisXcerpt_VLDB_2003, Author = {Berger, Sacha and Bry, Fran{\c c}ois and Schaffert, Sebastian and Wieser, Christoph}, Booktitle = VLDB, Conference-Abbr = {VLDB}, Keywords = {Xcerpt visXcerpt Query Languages Visualization}, Title = {{Xcerpt and visXcerpt: From Pattern-Based to Visual Querying of XML and Semistructured Data}}, Url = {http://www.pms.ifi.lmu.de/publikationen/#PMS-FB-2003-2}, Year = {2003}} @inproceedings{Berger.Bry.ea_VisualQueryingSemantic_ER_2004, Author = {Berger, Sacha and Bry, Fran{\c c}ois and Wieser, Christoph}, Booktitle = {Proc. Intl. Conf. on Conceptual Modeling}, Conference-Abbr = {ER}, Keywords = {REWERSE visXcerpt Visualization Query Languages Xcerpt}, Pdf = {SemanticWeb/REWERSE/Berger.Bry.ea_VisualQueryingSemantic_ER_2004.pdf}, Title = {{Visual Querying for the Semantic Web}}, Url = {http://rewerse.net/publications.html#REWERSE-RP-2004-43}, Year = {2004}, Abstract = {This paper presents a demonstration of visXcerpt, a visual query language for both, standard Web as well as Semantic Web applications.}} @article{Bex.Maneth.ea_FormalModelExpressive_IS_2002, Author = {Bex, Geert Jan and Maneth, Sebastian and Neven, Frank}, Doi = {http://dx.doi.org/10.1016/S0306-4379(01)00033-3}, Issn = {0306-4379}, Journal = {Information Systems}, Journal-Abbr = {IS}, Keywords = {XML XSLT formal expressiveness}, Number = {1}, Pages = {21--39}, Pdf = {QueryEvaluation/XML/XSLT/Bex.Maneth.ea_FormalModelExpressive_IS_2002.pdf}, Publisher = {Elsevier Science Ltd.}, Title = {{A Formal Model for an Expressive Fragment of XSLT}}, Url = {http://alpha.luc.ac.be/~lucg5503/xsltfull.ps}, Volume = {27}, Year = {2002}, Abstract = {The extension of the eXtensible Style sheet Language (XSL) by variables and passing of data values between template rules has generated a powerful XML query language: eXtensible Style sheet Language Transformations (XSLT). An informal introduction to XSTL is given, on the bases of which a formal model of a fragment of XSLT is defined. This formal model is in the spirit of tree transducers, and its semantics is defined by rewrite relations. It is shown that the expressive power of the fragment is already beyond that of most other XML query languages. Finally, important properties such as termination and closure under composition are considered.}} @inproceedings{BeyerCochrane.XQuery-for-Analytics.2004, Author = {Beyer, Kevin S. and Cochrane, Roberta and Colby, Latha S. and Ozcan, Fatma and Pirahesh, Hamid}, Booktitle = {Proc. of Intl. Workshop on XQuery Implementation, Experience and Perspectives $<$XIME-P/$>$}, Conference-Abbr = {XIME-P}, Date-Modified = {2005-05-21 17:58:53 +0200}, Keywords = {XQuery XML grouping analytics use cases group-by}, Owner = {Tim Furche}, Pages = {3-8}, Pdf = {QueryEvaluation/XML/XQuery/Grouping/Beyer.Cochrane.ea_XQueryAnalytics-Challenges_XIME-P_2004.pdf}, Title = {{XQuery for Analytics: Challenges and Requirements}}, Url = {http://www-rocq.inria.fr/gemo/Gemo/Projects/XIME-P/CR/PDF/BeyerCR.pdf}, Year = {2004}, Abstract = {XML has emerged as the industry standard for representing and exchanging data and is already predominant in several applications today. Business, analytic, and structured data will be exchanged as XML between applications and web services. XQuery is a query language that is emerging as the standard for querying XML data. The current version of the XQuery standard contains many features for navigating the hierarchical and ordered content of XML data. However, as compared to SQL, it lacks some key constructs which makes it di cult to succinctly express and e ciently execute some simple classes of analytic queries. In this paper, we describe some of the limitations of the current XQuery language and argue that extensions to XQuery are necessary to overcome these limitations.}} @techreport{Boag.Chamberlin.ea_XQuery1.0-XML_TR_2005, Author = {Boag, Scott and Chamberlin, Don and Fern{\'a}ndez, Mary F. and Florescu, Daniela and Robie, Jonathan and Sim{\'e}on, J{\'e}r{\^o}me}, Institution = {W3C}, Keywords = {XML XQuery W3C Query Query Languages}, Owner = {Tim Furche}, Title = {{XQuery 1.0: An XML Query Language}}, Type = {Working Draft}, Url = {http://www.w3.org/TR/xquery/}, Urldate = {2005/01/31}, Year = {2005}, Abstract = {XML is a versatile markup language, capable of labeling the information content of diverse data sources including structured and semi-structured documents, relational databases, and object repositories. A query language that uses the structure of XML intelligently can express queries across all these kinds of data, whether physically stored in XML or viewed as XML via middleware. This specification describes a query language called XQuery, which is designed to be broadly applicable across many types of XML data sources.}} @inproceedings{Boley_RuleMarkupLanguage_INAP_2001, Author = {Boley, Harold}, Bibsource = {DBLP, http://dblp.uni-trier.de}, Booktitle = {Intl. Conf. on Applications of Prolog}, Conference-Abbr = {INAP}, Ee = {http://link.springer.de/link/service/series/0558/bibs/2543/25430005.htm}, Keywords = {XML RDF RuleML data model integration role tags type tags}, Pages = {5-22}, Pdf = {SemanticWeb/RDF/RDF-XML-Integration/Boley_RuleMarkupLanguage_INAP_2001.pdf}, Title = {{The Rule Markup Language: RDF-XML Data Model, XML Schema Hierarchy, and XSL Transformations}}, Url = {http://iit-iti.nrc-cnrc.gc.ca/publications/nrc-47086_e.html}, Year = {2001}, Abstract = {Shared declarative aspects of Prolog and XML are examined. An XML version of pure Prolog is shown to be at the center of the Rule Markup Language. The RuleML data model uses Order-Labeled trees, combining the RDF and XML models. As part of RuleMl's hierarchy of sublanguages, the RuleML-Prolog DTD is employed for practical XML-to-XML and XML-to-(X)HTML transformation of Prolog on the Web.}} @mastersthesis{Bolzer_TowardsData-Integrationon_2005, Author = {Bolzer, Oliver}, Date-Modified = {2006-03-06 17:26:05 +0100}, Keywords = {XML Xcerpt RDF integration mediation views}, Owner = {Tim Furche}, School = {University of Munich}, Title = {{Towards Data-Integration on the Semantic Web: Querying RDF with Xcerpt}}, Type = {{Diplomarbeit/Master thesis}}, Url = {http://www.pms.ifi.lmu.de/publikationen#DA_Oliver.Bolzer}, Year = {2005}} @talk{Bolzer_SemanticWebQuerying_SLIDES_2004, Author = {Bolzer, Oliver}, Institution = {Institute for Computer Science, University of Munich, Germany}, Keywords = {RDF Semantic Web Xcerpt Views}, Owner = {Tim Furche}, Pdf = {SemanticWeb/Xcerpt/Bolzer_SemanticWebQuerying_SLIDES_2004.pdf}, Title = {{Semantic Web Querying Using Xcerpt}}, Type = {Oberseminar ?Knowledge Representation and Markup Languages?}, Year = {2004}, Abstract = {Xcerpt is a declarative, rule-based query and transformation language for XML and other semistructured data on the Web. This talk investigates the suitability of Xcerpt and it's underlying formalisms for querying and reasoning with both RDF and traditional XML data.}} @techreport{Bolzer.Bry.ea_DevelopmentofUse_TR_2005, Author = {Bolzer, Oliver and Bry, Fran{\c c}ois and Furche, Tim and Kraus, Sebastian and Schaffert, Sebastian}, Date-Modified = {2006-03-06 17:30:42 +0100}, Institution = {REWERSE}, Keywords = {REWERSE Query languages Use Cases Versatility Deliverable XML RDF}, Number = {I4-D3}, Owner = {Tim Furche}, Title = {{Development of Use Cases, Part I: Illustrating the Functionality of a Versatile Web Query Language}}, Type = {Deliverable}, Url = {http://rewerse.net/publications.html#REWERSE-DEL-2005-I4-D3}, Year = {2005}} @inproceedings{Bonifati.Braga.ea_ActiveXQuery_ICDE_2002, Author = {Bonifati, Angela and Braga, Daniele and Campi, Alessandro and Ceri, Stefano}, Booktitle = ICDE, Conference-Abbr = {ICDE}, Keywords = {XML XQuery update reactivity active}, Pages = {403}, Pdf = {QueryEvaluation/XML/XQuery/Bonifati.Braga.ea_ActiveXQuery_ICDE_2002.pdf}, Publisher = {IEEE Computer Society}, Title = {{Active XQuery}}, Url = {http://www.icar.cnr.it/angela/pubs/ICDE02.pdf}, Year = {2002}, Abstract = {Besides being adopted as the new interchange format for the Internet, XML is finding increasing acceptance as a native data repository language. In order to make XML repositories fully equipped with data management capabilities, suitable query and update languages are being developed. However, once the user is allowed to perform updates, it is perceivably necessary to guarantee the correctness of his/her updates, especially if document validity or semantic constraints are violated. We address this problem by exploiting the well-grounded concept of active rules.In this paper, we propose Active XQuery, an active language for XML repositories that is based on a previously defined XQuery update model. In particular, we present the syntax and semantics of our language, aiming at emulating the trigger definition and execution model of SQL3. An active extension of XQuery arises nontrivial problems, related to the need of interleaving updates and triggers. These problems have led us to define an algorithm for update reformulation and to devise a compact semantics. In conclusion, the paper presents an architecture for rapid prototyping, and hints optimization and research issues.}} @talk{Brade_TowardsAbstractMachine_SLIDES_2004, Author = {Brade, Michael}, Institution = {Institute for Computer Science, University of Munich, Germany}, Keywords = {Abstract Machine Query Evaluation Logic Programming Xcerpt Simulation Unification}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/AbstractMachines/Xcerpt/Brade_TowardsAbstractMachine_SLIDES_2004.pdf}, Title = {{Towards an Abstract Machine for Xcerpt?s Simulation Unification}}, Type = {Oberseminar ?Knowledge Representation and Markup Languages?}, Year = {2004}, Abstract = {This talk presents first steps in the direction of an abstract machine for the Simulation Unification in Xcerpt.}} @inproceedings{Braga.Campi.ea_XQuerybyExample_WWW_2003, Author = {Braga, Daniele and Campi, Alessandro and Ceri, Stefano and Augurusa, Enrico}, Booktitle = WWW, Conference-Abbr = {WWW}, Keywords = {XML query languages visualization XML-GL XQuery XQBE}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/Visualization/Braga.Campi.ea_XQuerybyExample_WWW_2003.pdf}, Title = {{XQuery by Example}}, Url = {http://www2003.org/cdrom/papers/poster/p291/p291-braga.html}, Year = {2003}, Abstract = {XQuery, the standard query language for XML, is gaining popularity among users with a SQL background; indeed, formulating XQuery and SQL queries requires comparable skills. However, this nucleus of programmers is not vast, and the availability of simpler XQuery ``dialects" could be valuable for establishing its success. With this motivation in mind, we designed XQBE, a visual dialect of XQuery inspired by QBE (Query by Example). QBE was initially proposed as alternative to SQL and has gained popularity as the language supported by MS Access, currently presented to users with a very limited experience of query languages. Coherent with the XML data model, XQBE uses one or more hierarchical structures to denote the input XML documents and one structure to denote the output document. Similar to QBE, structures are annotated to express selection predicates; explicit bindings between these structures visualize the input/output mappings.}} @inproceedings{Bremer.Gertz_XQuery-IR-IntegratingXML_WebDB_2002, Author = {Bremer, Jan-Marco and Gertz, Michael}, Booktitle = {Proc. Intl. Workshop on the Web and Databases}, Conference-Abbr = {WebDB}, Keywords = {XML XQuery IR information retrieval ranking query languages}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/InformationRetrieval/Languages/Bremer.Gertz_XQuery-IR-IntegratingXML_WebDB_2002.pdf}, Title = {{XQuery/IR: Integrating XML Document and Data Retrieval}}, Url = {http://www.db.ucsd.edu/webdb2002/papers/57.pdf}, Year = {2002}} @book{Brundage_XQuery-XMLQuery_2004, Author = {Brundage, Michael}, Keywords = {XML XQuery query languages}, Owner = {Tim Furche}, Publisher = {Addison-Wesley}, Title = {{XQuery: The XML Query Language}}, Year = {2004}} @inproceedings{Bruno.Maitre.ea_ExtendingXQuerywith_DocEng_2003, Author = {Bruno, Emmanuel and Maitre, Jacques Le and Murisasco, Elisabeth}, Booktitle = {Proc. ACM symposium on Document Engineering}, Conference-Abbr = {DocEng}, Date-Modified = {2005-05-21 18:05:17 +0200}, Doi = {http://doi.acm.org/10.1145/958220.958223}, Isbn = {1-58113-724-9}, Keywords = {XML XQuery transformations document engineering query languages}, Location = {Grenoble, France}, Pages = {1--8}, Pdf = {QueryEvaluation/XML/XQuery/LanguageConstructs/Bruno.Maitre.ea_ExtendingXQuerywith_DocEng_2003.pdf}, Publisher = {ACM Press}, Title = {{Extending XQuery with Transformation Operators}}, Url = {http://www.univ-tln.fr/~lemaitre/doceng2003.pdf}, Year = {2003}, Abstract = {In this paper, we propose to extend XQuery - the XML query language - with a set of transformation operators which will produce a copy of an XML tree in which some subtrees will be inserted, replaced or deleted. These operators - very similar to the ones proposed for updating an XML document - greatly simplify the expression of some queries in making it possible to express only the modified part of a tree instead of its whole reconstruction. We compare the expressivity of XQuery extended in this way with XSLT.}} @article{Brusilovsky_AdaptiveHypermedia_UMUAI_2001, Author = {Brusilovsky, Peter}, Journal = {User Modeling and User Adapted Interaction}, Journal-Abbr = {UMUAI}, Keywords = {Personalization Adaptive Hypermedia Adaptation}, Number = {1/2}, Owner = {Tim Furche}, Pages = {87-110}, Pdf = {ApplicationAreas/Personalization/Brusilovsky_AdaptiveHypermedia_UMUAI_2001.pdf}, Title = {{Adaptive Hypermedia}}, Url = {http://www2.sis.pitt.edu/~peterb/papers/brusilovsky-umuai-2001.pdf}, Volume = {11}, Year = {2001}, Abstract = {Adaptive Systems use explicit user models representing user knowledge, goals, interests, etc. that enable them to tailor interaction to different users. Adaptive hypermedia and AdaptiveWeb have used this paradigm to allow personalization in hypertext systems and the WWW, with diverse applications ranging from museum guides to web-based education. The goal of this chapter is to present the history of adaptive hypermedia, introduce a number of classic but popular techniques, and discuss emerging research directions in the context of the Adaptive and Semantic Web, that challenge the adaptive hypermedia researchers in the new Millennium.}} @book{Brusilovsky_AdaptiveHyperTextand_1998, Author = {Brusilovsky, Peter and Kobsa, Alfred and Vassileva, Julita}, Keywords = {Personalization Adaptation Adaptive Hypermedia}, Owner = {Tim Furche}, Publisher = {Kluwer Academic Publishers}, Title = {{Adaptive HyperText and Hypermedia}}, Url = {http://portal.acm.org/citation.cfm?id=551201&dl=ACM&coll=GUIDE}, Year = {1998}} @article{Brusilovsky.Maybury_FromAdaptiveHypermedia_CACM_2002, Author = {Brusilovsky, Peter and Maybury, Mark T.}, Journal = {Communications of the ACM}, Journal-Abbr = {CACM}, Keywords = {Personalization Adaptive Hypermedia Adaptation}, Number = {5}, Owner = {Tim Furche}, Pages = {30-33}, Title = {{From Adaptive Hypermedia to the Adaptive Web}}, Volume = {45}, Year = {2002}} @incollection{Brusilovsky.Nejdl_AdaptiveHypermediaand_2003, Author = {Brusilovsky, Peter and Nejdl, Wolfgang}, Booktitle = {Practical Handbook of Internet Computing}, Editor = {Munindar P. Singh}, Keywords = {Personalization Web Adaptive Hypermedia Adaptation}, Owner = {Tim Furche}, Pdf = {ApplicationAreas/Personalization/Brusilovsky.Nejdl_AdaptiveHypermediaand_2003.pdf}, Publisher = {CRC Press}, Title = {{Adaptive Hypermedia and Adaptive Web}}, Url = {http://www.kbs.uni-hannover.de/Arbeiten/Publikationen/2003/brusilovsky-nejdl.pdf}, Year = {2003}, Abstract = {Adaptive Systems use explicit user models representing user knowledge, goals, interests, etc. that enable them to tailor interaction to different users. Adaptive hypermedia and AdaptiveWeb have used this paradigm to allow personalization in hypertext systems and the WWW, with diverse applications ranging from museum guides to web-based education. The goal of this chapter is to present the history of adaptive hypermedia, introduce a number of classic but popular techniques, and discuss emerging research directions in the context of the Adaptive and Semantic Web, that challenge the adaptive hypermedia researchers in the new Millennium.}} @inproceedings{Bry.Coskun.ea_XMLStreamQuery_ICDE_2005, Author = {Bry, Fran{\c c}ois and Coskun, Fatih and Durmaz, Serap and Furche, Tim and Olteanu, Dan and Spannagel, Markus}, Booktitle = ICDE, Conference-Abbr = {ICDE}, Keywords = {Demo Streams Query Evaluation XPath XML REWERSE}, Organization = {IEEE}, Pdf = {QueryEvaluation/Streams/XPath/Bry.Coskun.ea_XMLStreamQuery_ICDE_2005.pdf}, Title = {{The XML Stream Query Processor SPEX}}, Url = {http://www.pms.ifi.lmu.de/publikationen/#PMS-FB-2005-1}, Urldate = {2004/11/11}, Year = {2005}, Abstract = {Data streams (e.g., [Koudas and Srivastava, VLDB, 2003]) are an emerging technology for data dissemination in cases where the data throughput or size make it unfeasible to rely on the conventional approach based on storing the data before processing it. Areas where data streams are applied include monitoring of scientific data (astronomy, meteorology), control data (traffic, logistics, networks), and financial data (bank transactions). Data streams are a new and promising setting in which many conventional database methods have to be considered anew. Querying XML data streams without storing and without decreasing considerably the data throughput is especially challenging because XML streams convey tree structured data with (possibly) unbounded size and depth. SPEX, initially described in [Olteanu et al., ICDE, 2002], evaluates XPath queries against XML data streams. SPEX is built upon formal frameworks for (1) rewriting XPath queries into equivalent XPath queries without reverse axes [Olteanu et al., EDBT-XMLDM, 2002] and (2) correct query evaluation with polynomial combined complexity using networks of pushdown transducers [Olteanu et al., SAC, 2004]. Such transducers are simple, independent, and can be connected in a flexible manner, thus allowing not only easy extensions but also extensive query optimization, e.g., by sharing transducers. A reason for the latter is that processing new query constructs implemented by new transducers does not affect the processing of existing ones. As a proof of concept, SPEX is extended here with novel compile-time optimizations that reduce both the size of the transducer network and the processing of irrelevant stream fragments. SPEX is demonstrated using a practically useful application for monitoring processes running on UNIX systems, and a novel, sophisticated visualization of its run-time system, called SPEX Viewer. SPEX Viewer makes it possible to visualize (1) the step-by-step rewriting of XPath queries into equivalent queries without reverse axes, (2) the networks of pushdown transducers generated from such queries, (3) the incremental processing of XML streams with these networks under various novel optimization settings, and (4) the progressive generation of answers.}} @inproceedings{Bry.Drabent.ea_OnSubtypingof_PPSWR_2004, Author = {Bry, Fran{\c c}ois and Drabent, W?odzimierz and Maluszynski, Jan}, Booktitle = PPSWR # {, St. Malo, France}, Conference-Abbr = {PPSWR}, Keywords = {REWERSE Typing Query Languages}, Organization = {REWERSE}, Pdf = {SemanticWeb/REWERSE/Bry.Drabent.ea_OnSubtypingof_PPSWR_2004.pdf}, Publisher = {Springer-Verlag}, Series = {LNCS}, Title = {{On Subtyping of Tree-structured Data A Polynomial Approach}}, Url = {http://rewerse.net/publications.html#REWERSE-RP-2004-11}, Volume = {3208}, Year = {2004}, Abstract = {This paper discusses subtyping of tree-structured data encountered on the Web, e.g. XML and HTML data. Our long range objective is to de ne a type system for Web and/or Semantic Web query languages amenable to static type checking. We propose a type formalism motivated by XML Schema and accommodating two concepts of subtyping: inclusion subtyping (corresponding to XML Schema notion of type restriction) and extension subtyping (motivated by XML Schema's type extension). We present algorithms for checking both kinds of subtyping. The algorithms are polynomial if certain conditions are imposed on the type de nitions; the conditions seem natural and not too restrictive.}} @talk{Bry.Furche_SurveyoverQuery_SLIDES_2004, Author = {Bry, Fran{\c c}ois and Furche, Tim}, Entrytype = {Principles underlying Xcerpt, a (Semantic) Web Query Language}, Institution = {Institute for Computer Science, University of Munich, Germany}, Keywords = {Design Query Languages Presentation REWERSE Survey}, Owner = {Tim Furche}, Pdf = {SemanticWeb/Xcerpt/Bry.Furche_SurveyoverQuery_SLIDES_2004.pdf}, Title = {{Survey over Query Languages for the (Semantic) Web}}, Type = {Oberseminar ?Knowledge Representation and Markup Languages?}, Year = {2004}, Abstract = {Proposal for a Classification Scheme and Exemplary Classifications}} @article{Bry.Furche.ea_QueryingWebReconsidered_JSWIS_2005, Author = {Bry, Fran{\c c}ois and Furche, Tim and Badea, Liviu and Koch, Christoph and Schaffert, Sebastian and Berger, Sacha}, Editor = {Tim Furche}, Journal = {Journal of Semantic Web and Information Systems}, Journal-Abbr = {JSWIS}, Keywords = {Semantic Web Xcerpt Design Query Languages Vision Versatile Query Language REWERSE}, Number = {2}, Pdf = {QueryEvaluation/SemanticWeb/Bry.Furche.ea_QueryingWebReconsidered_JSWIS_2004.pdf}, Title = {{Querying the Web Reconsidered: Design Principles for Versatile Web Query Languages}}, Volume = {1}, Year = {2005}, Abstract = {A decade of experience with research proposals as well as standardized query languages for the conventional Web and the recent emergence of query languages for the Semantic Web call for a reconsideration of design principles for Web and Semantic Web query languages. This article first argues that a new generation of versatile Web query languages is needed for solving the challenges posed by the changing Web: We call versatile those query languages able to cope with both Web and Semantic Web data expressed in any (Web or Semantic Web) markup language. This article further suggests that (well-known) referential transparency and (novel) answer-closedness are essential features of versatile query languages. Indeed, they allow queries to be considered like forms and answers like form-fillings in the spirit of the ?query-by-example? paradigm. This article finally suggests that the decentralized and heterogeneous nature of the Web requires incomplete data specifications (or ?incomplete queries?) and incomplete data selections (or ?incomplete answers?): the form-like query can be specified without precise knowledge of the queried data and answers can be restricted to contain only an excerpt of the queried data.}} @techreport{Bry.Furche.ea_IdentificationofDesign_TR_2004, Author = {Bry, Fran{\c c}ois and Furche, Tim and Badea, Liviu and Koch, Christoph and Schaffert, Sebastian and Berger, Sacha}, Date-Modified = {2006-03-06 17:23:38 +0100}, Editor = {Tim Furche}, Institution = {REWERSE}, Keywords = {Semantic Web Xcerpt Design Query Languages REWERSE}, Number = {I4-D2}, Pdf = {QueryEvaluation/SemanticWeb/Bry.Furche.ea_IdentificationofDesign_TR_2004.pdf}, Title = {{Identification of Design Principles}}, Type = {Deliverable}, Url = {http://rewerse.net/publications.html#REWERSE-DEL-2004-I4-D2}, Urldate = {2004/11/11}, Year = {2004}, Abstract = {This report identifies those design principles for a (possibly new) query and transformation language for the Web supporting inference that are considered essential. Based upon these design principles an initial strawman is selected. Scenarios for querying the Semantic Web illustrate the design principles and their reflection in the initial strawman, i.e., a first draft of the query language to be designed and implemented by the REWERSE working group I4.}} @article{Bry.Furche.ea_Datenstroeme_IS_2004, Author = {Bry, Fran{\c c}ois and Furche, Tim and Olteanu, Dan}, Journal = {Informatik Spektrum}, Journal-Abbr = {IS}, Keywords = {Query Evaluation Streams XML REWERSE}, Number = {2}, Pdf = {QueryEvaluation/Streams/Bry.Furche.ea_Datenstroeme_IS_2004.pdf}, Title = {{Datenstr{\"o}me}}, Url = {http://www.pms.ifi.lmu.de/publikationen/#PMS-FB-2004-2}, Urldate = {2004/11/11}, Volume = {27}, Year = {2004}, Abstract = {Unter einem ?Datenstrom? versteht man kontinuierlich {\"u}bersandte Datenstze, deren Gr{\"o}{\ss}e, Menge sowie schnelles Aufkommen verbieten, sie vor der Verarbeitung zu speichern. Die bisherige Forschung hat in erster Linie zum Ziel, Verfahren zu entwickeln, die es erlauben, ohne Verz{\"o}gerung des Datenflusses (1) einen Strom auf das Vorkommen von bestimmten Daten zu uberwachen und (2) die Daten aus einem Strom zu analysieren. Dieser Artikel dient als kurze Einf{\"u}hrung {\"u}ber Merkmale und aktuelle Forschungsergebnisse der Datenstr{\"o}menanfrage und -analyse.}} @inproceedings{Bry.Furche.ea_DataRetrievaland_PPSWR_2004, Author = {Bry, Fran{\c c}ois and Furche, Tim and P?tr{\^a}njan, Paula-Lavinia and Schaffert, Sebastian}, Booktitle = PPSWR, Conference-Abbr = {PPSWR}, Keywords = {Web Semantic Web Xcerpt XChange REWERSE}, Organization = {REWERSE}, Pdf = {SemanticWeb/Xcerpt/Bry.Furche.ea_DataRetrievaland_PPSWR_2004.pdf}, Publisher = {Springer-Verlag}, Series = {LNCS}, Title = {{Data Retrieval and Evolution on the (Semantic) Web: A Deductive Approach}}, Url = {http://www.pms.ifi.lmu.de/publikationen/#PMS-FB-2004-13}, Urldate = {2004/11/11}, Volume = {3208}, Year = {2004}, Abstract = {To make use of data represented on the Semantic Web, it is necessary to provide languages for Web data retrieval and evolution. This article introduces into the (conventional and Semantic) Web query language Xcerpt and the event and update language XChange, and shows how their deductive capabilities make them well suited for querying, changing and reasoning with data on both the conventional and the Semantic Web. To this aim, small application scenarios are introduced.}} @talk{Bry.Furche.ea_DesignPrinciplesI4_SLIDES_2004, Author = {Bry, Fran{\c c}ois and Furche, Tim and Schaffert, Sebastian}, Entrytype = {Principles underlying Xcerpt, a (Semantic) Web Query Language}, Institution = {REWERSE Working Groups ?Reasoning-aware Querying? and ?Evolution and Reactivity?, Munich, Germany}, Keywords = {Design Query Languages Xcerpt Presentation REWERSE}, Owner = {Tim Furche}, Pdf = {SemanticWeb/Xcerpt/Bry.Furche.ea_DesignPrinciplesI4_SLIDES_2004.pdf}, Title = {{Design Principles for I4 Query Language}}, Type = {Joint Workshop on Language Principles and State-of-the-Art}, Year = {2004}} @talk{Bry.Furche.ea_PrinciplesunderlyingXcerpt_SLIDES_2004, Author = {Bry, Fran{\c c}ois and Furche, Tim and Schaffert, Sebastian}, Entrytype = {Principles underlying Xcerpt, a (Semantic) Web Query Language}, Institution = {REWERSE Working Group ?Reasoning-aware Querying?, Vienna, Austria}, Keywords = {Design Query Languages Xcerpt Presentation REWERSE}, Owner = {Tim Furche}, Pdf = {SemanticWeb/Xcerpt/Bry.Furche.ea_PrinciplesunderlyingXcerpt_SLIDES_2004.pdf}, Title = {{Principles underlying Xcerpt, a (Semantic) Web Query Language}}, Type = {Kickoff-Workshop}, Year = {2004}} @article{Bry.Nagel.ea_Grid-Computing_IS_2004, Author = {Bry, Fran{\c c}ois and Nagel, Wolfgang E. and Schroeder, Michael}, Institution = {Institute of Informatics, University of Munich}, Journal = {Informatik Spektrum}, Journal-Abbr = {IS}, Keywords = {REWERSE Grid}, Number = {6}, Pdf = {SemanticWeb/REWERSE/Bry.Nagel.ea_Grid-Computing_IS_2004.pdf}, Title = {{Grid-Computing}}, Type = {{Forschungsbericht/research report}}, Url = {http://rewerse.net/publications.html#PMS-FB-2004-22}, Volume = {27}, Year = {2004}, Abstract = {"Grid-Computing", ein Mitte der 90er Jahre eingef{\"u}hrter Begriff, bezeichnet eine Architektur f{\"u}r verteilte Systeme, die auf dem World Wide Web aufbaut und die Web-Vision erweitert. Mit dem Grid-Computing werden die Ressourcen einer Gemeinschaft, einer sogenannten virtuellen Organisation (siehe unten), integriert. Die Hoffnung ist, dass hierdurch rechen- und/oder datenintensiven Aufgaben, die eine einzelne Organisation nicht l{\"o}sen kann, handhabbar werden. Ein Grid bezeichnet eine nach dem Grid-Computing-Ansatz aufgebaute Rechner-, Netzwerk- und Software-Infrastruktur zur Teilung von Ressourcen mit dem Ziel, die Aufgaben einer virtuellen Organisation zu erledigen. Zu Beginn war die M{\"o}glichkeit, ungenutzte CPU-Ressourcen an anderen Stellen f{\"u}r die eigenen Aufgaben einzusetzen, die wesentlich treibende Kraft f{\"u}r erste Experimente. Internet-Computing-Projekte wie SETI@Home, distributed.net u.a., bei denen die unbenutzten Rechenzyklen von weltweit verteilten privaten PCs verwendet werden, illustrieren das Potential des Grid-Computing. Die heutigen Grid-Konzepte und die ersten -Prototypen gehen weit {\"u}ber diese Anfnge hinaus. Sie versprechen die transparente Bereitstellung von Diensten unabhngig von der rumlichen Nhe. Es wird erwartet, dass das Grid-Computing die Nutzung von Rechnern und Rechnernetzen so grundlegend verndern wird, wie das Web den Datenaustausch bereits verndert hat.}} @inproceedings{Bry.Patranjan_ReactivityonWeb_SAC_2005, Author = {Bry, Fran{\c c}ois and P?tr{\^a}njan, Paula-Lavinia}, Booktitle = SAC, Conference-Abbr = {SAC}, Keywords = {REWERSE Reactivity XChange}, Organization = {ACM}, Title = {{Reactivity on the Web: Paradigms and Applications of the Language XChange}}, Url = {http://rewerse.net/publications.html#REWERSE-RP-2004-41}, Year = {2005}, Abstract = {Reactivity on the Web is an emerging issue. It is essential for upcoming Web systems such as online marketplaces, adaptive, Semantic Web systems as well as Web services and Grids. This article first introduces the paradigms upon which the high-level language XChange for programming reactive behaviour and distributed applications on the Web relies. Then, it briefly presents the main syntactical constructs of XChange. Finally, it sketches the implementation in XChange of a reactive Web-based application.}} @inproceedings{Bry.Patranjan.ea_XcerptandXChange_ICLP_2004, Author = {Bry, Fran{\c c}ois and P{\u a}tr{\^a}njan, Paula-Lavinia and Schaffert, Sebastian}, Booktitle = ICLP, Conference-Abbr = {ICLP}, Date-Modified = {2006-03-06 17:27:04 +0100}, Keywords = {REWERSE Query Languages Reactivity Xcerpt XChange}, Publisher = {Springer-Verlag}, Series = {LNCS}, Title = {{Xcerpt and XChange: Logic Programming Languages for Querying and Evolution on the Web}}, Url = {http://www.pms.ifi.lmu.de/publikationen#PMS-FB-2004-11}, Year = {2004}} @inproceedings{Bry.Schaffert_EntailmentRelationReasoning_RuleML_2003, Author = {Bry, Fran{\c c}ois and Schaffert, Sebastian}, Booktitle = {Proc. Workshop on Rules and Rule Markup Languages for the Semantic Web}, Conference-Abbr = {RuleML}, Keywords = {Xcerpt Semantics Entailment Reasoning}, Pdf = {SemanticWeb/Xcerpt/Bry.Schaffert_EntailmentRelationReasoning_RuleML_2003.pdf}, Publisher = {Springer-Verlag}, Series = {LNCS}, Title = {{An Entailment Relation for Reasoning on the Web}}, Url = {http://www.pms.ifi.lmu.de/publikationen/#PMS-FB-2003-5}, Volume = {2876}, Year = {2003}, Abstract = {Reasoning on the Web is receiving an increasing attention because of emerging fields such as Web adaption and Semantic Web. Indeed, the advanced functionalities striven for in these fields call for reasoning capabilities. Reasoning on the Web, however, is usually done using existing techniques rarely fitting the Web. As a consequence, additional data processing like data conversion from Web formats (e.g. XML or HTML) into some other formats (e.g. classical logic terms and formulas) is often needed and aspects of the Web (e.g. its inherent inconsistency) are neglected. This article first gives requirements for an entailment tuned to reasoning on the Web. Then, it describes how classical logic's entailment can be modified so as to enforce these requirements. Finally, it discusses how the proposed entailment can be used in applying logic programming to reasoning on the Web.}} @inproceedings{Bry.Schaffert_GentleIntroductioninto_RuleML-WS_2002, Author = {Bry, Fran{\c c}ois and Schaffert, Sebastian}, Booktitle = {Proc. Intl. Workshop on Rule Markup Languages for Business Rules on the Semantic Web}, Conference-Abbr = {RuleML-WS}, Keywords = {XML Xcerpt introduction query languages}, Pdf = {QueryEvaluation/Xcerpt/Bry.Schaffert_GentleIntroductioninto_RuleML-WS_2002.pdf}, Title = {{A Gentle Introduction into Xcerpt, a Rule-based Query and Transformation Language for XML}}, Url = {http://www.pms.ifi.lmu.de/publikationen/#PMS-FB-2002-11}, Year = {2002}, Abstract = {This articles introduces into Xcerpt, a rule-based query and transformation language for XML. First, the design principles of Xcerpt are given. Then, the essential construct of Xcerpt are explained and illustrated on examples: "query terms", i.e. patterns using which Xcerpt queries are posed, "construct terms", i.e. pattern re-assembling the data selected in a query term into a new data item, and "construct-query rule" linking queries with construct terms. Then, Xcerpt and XQuery are compared on examples and the advantages of Xcerpt are discussed. Finally, an outlook into Xcerpt's declarative and procedural semantics as well as into Xcerpt's features currently developed are given.}} @inproceedings{Bry.Schaffert_TowardsDeclarativeQuery_ICLP_2002, Author = {Bry, Fran{\c c}ois and Schaffert, Sebastian}, Booktitle = ICLP, Conference-Abbr = {ICLP}, Date-Modified = {2006-03-06 17:47:44 +0100}, Keywords = {Xcerpt Query Languages XML}, Pdf = {SemanticWeb/Xcerpt/Bry.Schaffert_TowardsDeclarativeQuery_ICLP_2002.pdf}, Publisher = {Springer-Verlag}, Series = {LNCS}, Title = {{Towards a Declarative Query and Transformation Language for XML and Semistructured Data: Simulation Unification}}, Url = {http://www.pms.ifi.lmu.de/publikationen#PMS-FB-2002-19}, Volume = {2401}, Year = {2002}, Abstract = {The growing importance of XML as a data interchange standard demands languages for data querying and transformation. Since the mid 90es, several such languages have been proposed that are inspired from functional languages (such as XSLT) and/or database query languages (such as XQuery). This paper addresses applying logic programming concepts and techniques to designing a declarative, rule-based query and transformation language for XML and semistructured data.The paper first introduces issues specific to XML and semistructured data such as the necessity of flexible "query terms" and of "construct terms". Then, it is argued that logic programming concepts are particularly appropriate for a declarative query and transformation language for XML and semistructured data. Finally, a new form of unification, called "simulation unification", is proposed for answering "query terms", and it is illustrated on examples.}} @inproceedings{Bry.Schaffert_XMLQueryLanguage_GI-WebDB_2002, Author = {Bry, Fran{\c c}ois and Schaffert, Sebastian}, Booktitle = {Proc. Intl. Workshop on Web and Databases}, Conference-Abbr = {GI-WebDB}, Date-Modified = {2006-03-06 17:47:17 +0100}, Keywords = {XML Xcerpt principles query languages}, Pdf = {QueryEvaluation/Xcerpt/Bry.Schaffert_XMLQueryLanguage_GI-WebDB_2002.pdf}, Publisher = {Springer-Verlag}, Series = {LNCS}, Title = {{The XML Query Language Xcerpt: Design Principles, Examples, and Semantics}}, Url = {http://www.pms.ifi.lmu.de/publikationen#PMS-FB-2002-7}, Volume = {2593}, Year = {2002}, Abstract = {Most query and transformation languages developed since the mid 90es for XML and semistructured data -- e.g. XQuery, the precursors of XQuery, and XSLT -- build upon a path-oriented node selection: A node in a data item is specified in terms of a root-to-node path in the manner of the file selection languages of operating systems. Constructs inspired from the regular expression constructs *, +, ?, and "wildcards" give rise to a flexible node retrieval from incompletely specified data items.This paper further introduces into Xcerpt, a query and transformation language further developing an alternative approach to querying XML and semistructured data first introduced with the language UnQL. A metaphor for this approach views queries as patterns, answers as data items matching the queries. Formally, an answer to a query is defined as a simulation of an instance of the query in a data item.}} @inproceedings{Bry.Schaffert.ea_XcerptandXChange_SWSDN_2004, Author = {Bry, Fran{\c c}ois and Schaffert, Sebastian and P?tr{\^a}njan, Paula-Lavinia}, Booktitle = {Proc. Workshop on Semantic Web Services and Dynamic Networks}, Conference-Abbr = {SWSDN}, Keywords = {REWERSE Xcerpt XChange Query Languages Reactivity}, Organization = {GI}, Pdf = {SemanticWeb/REWERSE/Bry.Schaffert.ea_XcerptandXChange_SWSDN_2004.pdf}, Title = {{Xcerpt and XChange: Deductive Languages for Data Retrieval and Evolution on the Web}}, Url = {http://rewerse.net/publications.html#REWERSE-RP-2004-21}, Year = {2004}, Abstract = {In this article, two deductive languages are introduced: the language Xcerpt, for querying data and reasoning with data on the (Semantic) Web, and the language XChange, for evolution and reactivity on the (Semantic) Web. A small application scenario is given as a motivation for these languages.}} @inproceedings{Bry.Schaffert.ea_contributiontoSemantics_WLP_2004, Author = {Bry, Fran{\c c}ois and Schaffert, Sebastian and Schr{\"o}der, Andreas}, Booktitle = {Proc. Workshop on (Constraint) Logic Programming}, Conference-Abbr = {WLP}, Keywords = {REWERSE Query Evaluation Xcerpt Semantics}, Organization = {GLP, GI}, Pdf = {SemanticWeb/REWERSE/Bry.Schaffert.ea_contributiontoSemantics_WLP_2004.pdf}, Title = {{A contribution to the Semantics of Xcerpt, a Web Query and Transformation Language}}, Url = {http://rewerse.net/publications.html#REWERSE-RP-2004-18}, Year = {2004}, Abstract = {Xcerpt is a declarative and pattern-based query and transformation language for the Web with deductive capabilities. In contrast to Web query languages like XQuery and XSLT, Xcerpt relies on concepts and techniques from logic programming and automated theorem proving such as declarative ?query patterns? and ?rule chaining?. Xcerpt can also be used for querying Web metadata, like OWL or RDF data, and reasoning on such metadata. In contrast to specific languages for OWL and RDF, however, Xcerpt is a general purpose query, transformation, and reasoning language, i.e. it can be used for reasoning not only with Web metadata but also with plain Web data. Salient aspects of Xcerpt are its nonstandard ?query patterns? for retrieving incompletely specified data and its unusual ?grouping constructs? some and all that significantly depart from the standard approaches in logic programming or automated theorem proving. Xcerpt relies on a new, assymmetric unification, called simulation unification for evaluating query patterns that incompletely specify data. Furthermore, Xcerpt does not rely on meta reasoning for expressing and processing ?grouping? constructs corresponding to Prolog?s metalevel predicates setof and bagof. This article gives a brief overview over challenges of applying logic programming techniques to Web querying. In particular it suggests two different approaches for treating the meta-level grouping constructs all and some in a proof calculus formalising the operational semantics of Xcerpt.}} @inproceedings{Bry.Spranger_TowardsMulti-CalendarTemporal_PPSWR_2004, Author = {Bry, Fran{\c c}ois and Spranger, Stephanie}, Booktitle = PPSWR, Conference-Abbr = {PPSWR}, Keywords = {REWERSE Xcerpt CATTS Temporal Reasoning}, Organization = {REWERSE}, Pdf = {SemanticWeb/REWERSE/Bry.Spranger_TowardsMulti-CalendarTemporal_PPSWR_2004.pdf}, Publisher = {Springer-Verlag}, Series = {LNCS}, Title = {{Towards a Multi-Calendar Temporal Type System for (Semantic) Web Query Languages}}, Url = {http://rewerse.net/publications.html#REWERSE-RP-2004-19}, Volume = {3208}, Year = {2004}, Abstract = {Time is omnipresent on the (Semantic) Web. However, for- malism like XML, XML Schema, RDF, OWL and (Semantic) Web query languages have, if any, only very limited notions of temporal data types and temporal theories built-in. Recently, the development of Web Ser- vices for temporal operations has begun. In this article, we describe a connection, possibly the rst one, between such Web Services and Web formalisms: A proposal of a type system for temporal and calendric data, called multi-calendar temporal type system seamlessly integrated into a host (query) language. The type system's associated type checking meth- ods are beyond the scope of this article. For proof-of-concept purposes, the Web and Semantic Web query language Xcerpt has been chosen.}} @inproceedings{Buneman.Semistructured-data.1997, Author = {Buneman, Peter}, Booktitle = {Proc. ACM Symposium on Principles of Database Systems}, Conference-Abbr = {PODS}, Date-Modified = {2005-04-12 21:38:08 +0200}, Doi = {http://doi.acm.org/10.1145/263661.263675}, Isbn = {0-89791-910-6}, Location = {Tucson, Arizona, United States}, Pages = {117--121}, Publisher = {ACM Press}, Title = {{Semistructured Data}}, Year = {1997}} @inproceedings{Buneman.Davidson.ea_QueryLanguageand_SIGMOD_1996, Author = {Buneman, Peter and Davidson, Susan and Hillebrand, Gerd and Suciu, Dan}, Booktitle = SIGMOD, Conference-Abbr = {SIGMOD}, Doi = {http://doi.acm.org/10.1145/233269.233368}, Isbn = {0-89791-794-4}, Keywords = {XML query languages UnQL}, Location = {Montreal, Quebec, Canada}, Pages = {505--516}, Pdf = {QueryEvaluation/XML/Buneman.Davidson.ea_QueryLanguageand_SIGMOD_1996.pdf}, Publisher = {ACM Press}, Title = {{A Query Language and Optimization Techniques for Unstructured Data}}, Url = {http://www.cs.washington.edu/homes/suciu/camera-ready-final.ps}, Year = {1996}, Abstract = {A new kind of data model has recently emerged in which the database is not constrained by a conventional schema. Systems like ACeDB, which has become very popular with biologists, and the recent Tsimmis proposal for data integration organize data in tree-like structures whose components can be used equally well to represent sets and tuples. Such structures allow great flexibility y in data representation.What query language is appropriate for such structures? Here we propose a simple language UnQL for querying data organized as a rooted, edge-labeled graph. In this model, relational data may be represented as fixed-depth trees, and on such trees UnQL is equivalent to the relational algebra. The novelty of UnQL consists in its programming constructs for arbitrarily deep data and for cyclic structures. While strictly more powerful than query languages with path expressions like XSQL, UnQL can still be efficiently evaluated. We describe new optimization techniques for the deep or "vertical" dimension of UnQL queries. Furthermore, we show that known optimization techniques for operators on flat relations apply to the "horizontal" dimension of UnQL.}} @inproceedings{Buneman.Davidson.ea_ProgrammingConstructsUnstructured_DBLP_1996, Author = {Buneman, Peter and Davidson, Susan B. and Suciu, Dan}, Booktitle = {Proc. Intl. Workshop on Database Programming Languages}, Conference-Abbr = {DBLP}, Isbn = {3-540-76086-5}, Keywords = {XML query languages UnQL structural recursion}, Pages = {12}, Pdf = {QueryEvaluation/XML/Buneman.Davidson.ea_ProgrammingConstructsUnstructured_DBLP_1996.pdf}, Publisher = {Springer-Verlag}, Title = {{Programming Constructs for Unstructured Data}}, Url = {http://www.cs.washington.edu/homes/suciu/file32_paper.ps}, Year = {1996}} @techreport{BuxtonRys.XQuery-and-XPath-Ful.2003, Author = {Buxton, Stephen and Rys, Michael}, Date-Added = {2005-04-30 22:26:07 +0200}, Date-Modified = {2005-04-30 22:31:13 +0200}, Institution = {W3C}, Keywords = {XML XQuery full-text information retrieval requirements}, Title = {{XQuery and XPath Full-Text Requirements}}, Type = {Working Draft}, Url = {http://www.w3.org/TR/xquery-full-text-requirements/}, Year = {2003}, Abstract = {The document specifies requirements for Full-Text search for use in XQuery [XQuery] and XPath [XPath].}} @inproceedings{Calvanese.Giacomo.ea_ContainmentofConjunctive_KR_2000, Author = {Calvanese, Diego and Giacomo, Giuseppe De and Lenzerini, Maurizio and Vardi, Moshe Y.}, Booktitle = {Proc. Intl. Conf. on the Principles of Knowledge Representation and Reasoning}, Conference-Abbr = {KR}, Keywords = {query processing containment path expressions inverse conjunctive}, Pages = {176--185}, Pdf = {QueryEvaluation/Languages/Calvanese.Giacomo.ea_ContainmentofConjunctive_KR_2000.pdf}, Title = {{Containment of Conjunctive Regular Path Queries with Inverse}}, Url = {http://www.inf.unibz.it/%7ecalvanese/papers/calv-degi-lenz-vard-KR-2000.ps.gz}, Year = {2000}, Abstract = {Reasoning on queries is a basic problem both in knowledge representation and databases. A fundamental form of reasoning on queries is checking containment, i.e., verifying whether one query yields necessarily a subset of the result of another query. Query containment is crucial in several contexts, such as query optimization, knowledge base verification, information integration, database integrity checking, and cooperative answering. In this paper we address the problem of query containment in the context of semistructured knowledge bases, where the basic querying mechanism, namely regular path queries, asks for all pairs of objects that are connected by a path conforming to a regular expression. We consider conjunctive regular path queries with inverse, which extend regular path queries with the possibility of using both the inverse of binary relations, and conjunctions of atoms, where each atom specifies that one regular path query with inverse holds between two variables. We present a novel technique to check containment of queries in this class, based on the use of two-way finite automata. The technique shows the power of two-way automata in dealing with the inverse operator and with the variables in the queries. We also characterize the computational complexity of both the proposed algorithm and the problem.}} @inproceedings{Calvanese.Giacomo.ea_QueryProcessingusing_PODS_2000, Author = {Calvanese, Diego and Giacomo, Giuseppe De and Lenzerini, Maurizio and Vardi, Moshe Y.}, Booktitle = PODS, Conference-Abbr = {PODS}, Keywords = {conjunctive queries query languages regular path expressions inverse views optimization}, Pages = {58--66}, Pdf = {QueryEvaluation/Languages/Calvanese.Giacomo.ea_QueryProcessingusing_PODS_2000.pdf}, Title = {{Query Processing using Views for Regular Path Queries with Inverse}}, Url = {http://www.inf.unibz.it/%7ecalvanese/papers/calv-degi-lenz-vard-PODS-2000.ps.gz}, Year = {2000}, Abstract = {Query processing using views is the problem of computing the answer to a query based on a set of materialized views, rather than on the raw data in the database. The problem comes in two different forms, called query rewriting and query answering, respectively. In the first form, we are given a query and a set of view definitions, and the goal is to reformulate the query into an expression that refers only to the views. In the second form, besides the query and the view definitions, we are also given the extensions of the views and a tuple, and the goal is to check whether the knowledge on the view extensions logically implies that the tuple satisfies the query. In this paper we address the problem of query processing using views in the context of semistructured data, in particular for the case of regular path queries extended with the inverse operator. Several authors point out that the inverse operator is one of the fundamental extensions for making regular path queries useful in real settings. We present a novel technique based on the use of two-way finite automata. Our approach demonstrates the power of this kind of automata in dealing with the inverse operator, allowing us to show that both query rewriting and query answering with the inverse operator has the same computational complexity as for the case of standard regular path queries.}} @article{Cardelli.Ghelli_TQL-QueryLanguage_MSCS_2004, Author = {Cardelli, Luca and Ghelli, Giorgio}, Doi = {http://dx.doi.org/10.1017/S0960129504004141}, Issn = {0960-1295}, Journal = {Mathematical Structures in Computer Science}, Journal-Abbr = {MSCS}, Keywords = {XML query languages TQL ambient logic pattern path TQL}, Number = {3}, Pages = {285--327}, Pdf = {QueryEvaluation/XML/LogicProgrammingApproaches/Cardelli.Ghelli_TQL-QueryLanguage_MSCS_2004.pdf}, Publisher = {Cambridge University Press}, Title = {{TQL: a Query Language for Semistructured Data based on the Ambient Logic}}, Url = {http://research.microsoft.com/Users/luca/Papers/A%20Query%20Language%20Based%20on%20the%20Ambient%20Logic%20MSCS.A4.pdf}, Volume = {14}, Year = {2004}, Abstract = {The ambient logic is a modal logic that was proposed for the description of the structural and computational properties of distributed and mobile computation. The structural part of the ambient logic is, essentially, a logic of labelled trees, hence it turns out to be a good foundation for query languages for semistructured data, much in the same way as first-order logic is a fitting foundation for relational query languages. We define here a query language for semistructured data that is based on the ambient logic, and we outline an execution model for this language. The language turns out to be quite expressive. Its strong foundations and the equivalences that hold in the ambient logic are helpful in the definition of the language semantics and execution model.}} @inproceedings{Cardelli.Gordon_AnytimeAnywhere-Modal_POPL_2000, Author = {Cardelli, Luca and Gordon, Andrew D.}, Booktitle = {Proc. Symposium on Principles of Programming Languages}, Conference-Abbr = {POPL}, Doi = {http://doi.acm.org/10.1145/325694.325742}, Isbn = {1-58113-125-9}, Keywords = {XML query languages ambient logic pattern TQL}, Location = {Boston, MA, USA}, Pages = {365--377}, Pdf = {QueryEvaluation/XML/Cardelli.Gordon_AnytimeAnywhere-Modal_POPL_2000.pdf}, Publisher = {ACM Press}, Title = {{Anytime, Anywhere: Modal Logics for Mobile Ambients}}, Url = {http://research.microsoft.com/~adg/Talks/990506-logic.pdf}, Year = {2000}, Abstract = {The Ambient Calculus is a process calculus where processes may reside within a hierarchy of locations and modify it. The purpose of the calculus is to study mobility, which is seen as the change of spatial configurations over time. In order to describe properties of mobile computations we devise a modal logic that can talk about space as well as time, and that has the Ambient Calculus as a model.}} @inproceedings{Ceri.Comai.ea_XML-GL-GraphicalLanguage_WWW_1999, Author = {Ceri, Stefano and Comai, Sara and Damiani, Ernesto and Fraternali, Piero and Paraboschi, Stefano and Tanca, Letizia}, Booktitle = WWW, Conference-Abbr = {WWW}, Keywords = {XML query languages XML-GL visual visualization}, Owner = {Tim Furche}, Title = {{XML-GL: a Graphical Language for Querying and Restructuring XML Documents}}, Url = {http://www8.org/w8-papers/1c-xml/xml-gl/xml-gl.html}, Year = {1999}, Abstract = {The widespreading of XML as a standard for semi-structured documents on the Web opens up challenging opportunities for Web query languages. In this paper we introduce XML-GL, a graphical query language for XML documents. The use of a visual formalism for representing both the content of XML documents (and of their DTDs) and the syntax and semantics of queries enables an intuitive expression of queries, even when they are rather complex. XML-GL is inspired by G-log, a general purpose, logic-based language for querying structured and semi-structured data. The paper presents the basic capabilities of XML-GL through a sequence of examples of increasing complexity.}} @inproceedings{Ceri.Comai.ea_XML-GL-GraphicalLanguage_QL98_1998, Author = {Ceri, Stefano and Comai, Sara and Damiani, Ernesto and Fraternali, Piero and Paraboschi, Stefano and Tanca:, Letizia}, Booktitle = PROC # {W3C QL'98 -- Query Languages}, Conference-Abbr = {QL98}, Keywords = {XML query languages visual}, Owner = {Tim Furche}, Title = {{XML-GL: A Graphical Language for Querying and Reshaping XML Documents}}, Url = {http://www.w3.org/TandS/QL/QL98/pp/xml-gl.html}, Year = {1998}, Abstract = {We present XML-GL, a graphical query language for XML documents. XML-GL derives from GLog a general purpose, logic- and graph-based language for querying structured and semi-structured data. Here we list a number of interesting requirements for a query language for XML documents, and give a few examples of XML-GL features addressing such requirements.}} @techreport{Chamberlin.Frankhauser.ea_XMLQueryUse_TR_2005, Author = {Chamberlin, Don and Frankhauser, Peter and Florescu, Daniela and Marchiori, Massimo and Robie, Jonathan}, Institution = {W3C}, Keywords = {XML XQuery Use Cases W3C Query Query Languages}, Owner = {Tim Furche}, Title = {{XML Query Use Cases}}, Type = {Working Draft}, Url = {http://www.w3.org/TR/xquery-use-cases/}, Urldate = {2005/01/31}, Year = {2005}} @techreport{Chamberlin.Frankhauser.ea_XMLQueryUse_TR_2001, Author = {Chamberlin, Don and Frankhauser, Peter and Marchiori, Massimo and Robie, Jonathan}, Institution = {W3C}, Keywords = {XML XQuery Use Cases W3C Query Query Languages}, Owner = {Tim Furche}, Title = {{XML Query Use Cases}}, Type = {Working Draft}, Url = {http://www.w3.org/TR/2001/WD-xmlquery-use-cases-20010215}, Urldate = {2005/01/31}, Year = {2001}} @techreport{Chamberlin.Robie_XQueryUpdateFacility_TR_2005, Author = {Chamberlin, Don and Robie, Jonathan}, Institution = {W3C}, Keywords = {XML XQuery update reactivity requirements}, Owner = {Tim Furche}, Title = {{XQuery Update Facility Requirements}}, Type = {Working Draft}, Url = {http://www.w3.org/TR/xquery-update-requirements/}, Year = {2005}, Abstract = {This document specifies goals and requirements for the XQuery Update Facility.}} @inproceedings{Chen.Rundensteiner_ACE-XQ-CachE-awareXQuery_WebDB_2002, Author = {Chen, L. and Rundensteiner, E. A.}, Booktitle = PROC # {Workshop on the Web and Databases}, Conference-Abbr = {WebDB}, Keywords = {XML XQuery views processing evaluation}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/XQuery/Chen.Rundensteiner_ACE-XQ-CachE-awareXQuery_WebDB_2002.pdf}, Title = {{ACE-XQ: A CachE-aware XQuery Answering System}}, Url = {http://www.cs.wpi.edu/~lichen/papers/webdb02-acexq.ps}, Year = {2002}} @inproceedings{Chen.Jagadish.ea_FromTreePatterns_VLDB_2003, Author = {Chen, Zhimin and Jagadish, H. V. and Lakshmanan, Laks V.S. and Paparizos, Stelios}, Booktitle = VLDB, Conference-Abbr = {VLDB}, Keywords = {XML XQuery optimization generalized tree patterns nested queries}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/XQuery/Chen.Jagadish.ea_FromTreePatterns_VLDB_2003.pdf}, Title = {{From Tree Patterns to Generalized Tree Patterns: On Efficient Evaluation of XQuery}}, Url = {http://www.vldb.org/conf/2003/papers/S08P03.pdf}, Year = {2003}, Abstract = {XQuery is the de facto standard XML query language, and it is important to have e cient query evaluation techniques available for it. A core operation in the evaluation of XQuery is the nding of matches for speci ed tree patterns, and there has been much work towards algorithms for nding such matches e ciently. Multiple XPath expressions can be evaluated by computing one or more tree pattern matches. However, relatively little has been done on e - cient evaluation of XQuery queries as a whole. In this paper, we argue that there is much more to XQuery evaluation than a tree pattern match. We propose a structure called generalized tree pat- tern (GTP) for concise representation of a whole XQuery expression. Evaluating the query reduces to nding matches for its GTP. Using this idea we develop e cient evaluation plans for XQuery expressions, possibly involving join, quanti ers, grouping, aggregation, and nesting. XML data often conforms to a schema. We show that using relevant constraints from the schema, one can optimize queries signi cantly, and give algorithms for automatically inferring GTP simpli cations given a schema. Finally, we show, through a detailed set of experiments using the TIMBER XML database system, that plans via GTPs (with or without schema knowledge) signi cantly outperform plans based on navigation and straightforward plans obtained directly from the query.}} @article{Chinenyanga.Kushmerick_ExpressiveandEfficient_JIST_2002, Author = {Chinenyanga, Taurai Tapiwa and Kushmerick, Nicholas}, Journal = {Journal of the American Society for Information Science and Technology}, Journal-Abbr = {JIST}, Keywords = {XML IR information retrieval ranking query languages}, Number = {6}, Owner = {Tim Furche}, Pages = {438--453}, Title = {{An Expressive and Efficient Language for XML Information Retrieval}}, Volume = {53}, Year = {2002}, Abstract = {Several languages for querying and transforming XML, including XML-QL, Quilt, and XQL, have been proposed. However, these languages do not support ranked queries based on textual similarity, in the spirit of traditional IR. Several extensions to these XML query languages to support keyword search have been made, but the resulting languages cannot express IR-style queries such as "find books and CDs with similar titles." In some of these languages keywords are used merely as boolean filters without support for true ranked retrieval; others permit similarity calculations only between a data value and a constant, and thus cannot express the above query. WHIRL avoids both problems, but assumes relational data. We propose ELIXIR, an expressive and efficient language for XML information retrieval that extends XML-QL with a textual similarity operator that can be used for similarity joins, so ELIXIR is sufficiently expressive to handle the sample query above. ELIXIR thus qualifies as a general-purpose XML IR query language. Our central contribution is an efficient algorithm for answering ELIXIR queries that rewrites the original ELIXIR query into a series of XML-QL queries to generate intermediate relational data, and uses WHIRL to efficiently evaluate the similarity operators on this intermediate data, yielding an XML document with nodes ranked by similarity. Our experiments demonstrate that our prototype scales well with the size of the query and the XML data.}} @techreport{Clark_RDFDataAccess_TR_2004, Author = {Clark, Kendall Grant}, Institution = {W3C}, Keywords = {RDF Data Access Use Cases W3C Query Query Languages Requirements}, Owner = {Tim Furche}, Title = {{RDF Data Access Use Cases and Requirements}}, Type = {Working Draft}, Url = {http://www.w3.org/TR/rdf-dawg-uc/}, Urldate = {2005/01/31}, Year = {2004}, Abstract = {This document specifies use cases, requirements, and objectives for an RDF query language and data access protocol. It suggests how an RDF query language and data access protocol could be used in the construction of novel, useful Semantic Web applications in areas like web publishing, personal information management, transportation, and tourism.}} @inproceedings{Coelho.Florido_Type-basedXMLProcessing_PADL_2003, Author = {Coelho, Jorge and Florido, M.}, Booktitle = {Proc. Intl. Symp. on Practical Aspects of Declarative Languages (PADL), New Orleans, Louisiana, USA}, Comment = {READ}, Conference-Abbr = {PADL}, Keywords = {XML Query Evaluation Logic Programming Typing}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/LogicProgrammingApproaches/Coelho.Florido_Type-basedXMLProcessing_PADL_2003.pdf}, Publisher = {Springer-Verlag}, Series = {LNCS}, Title = {{Type-based XML Processing in Logic Programming}}, Url = {http://www.dei.isep.ipp.pt/~jcoelho/x-prolog/padl03.pdf}, Urldate = {2004/11/17}, Volume = {2562}, Year = {2003}, Abstract = {In this paper we propose a type-based framework for using logic programming for XML processing. We transform XML documents into terms and DTDs into regular types. We implemented a standard type inference algorithm for logic programs and use the types corresponding to the DTDs as additional type declarations for logic programs for XML processing. Due to the correctness of the type inference this makes it possible to use logic programs as an implicitly typed processing language for XML with static type (in this case DTDs) validation. As far as we know this is the first work adding type validation at compile time to the use of logic programming for XML processing.}} @inproceedings{Coelho.Florido_CLPFlex-ConstraintLogic_ODBASE_2004, Author = {Coelho, Jorge and Florido, M{\'a}rio}, Booktitle = ODBASE, Conference-Abbr = {ODBASE}, Keywords = {XML Query languages Prolog Logic Programming Constraint Programming}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/LogicProgrammingApproaches/Coelho.Florido_CLP(Flex)-ConstraintLogic_ODBASE_2004.pdf}, Publisher = {Springer-Verlag}, Series = {LNCS}, Title = {{CLP(Flex): Constraint Logic Programming Applied to XML Processing}}, Url = {http://www.ncc.up.pt/~jcoelho/clpflex.pdf}, Volume = {3291}, Year = {2004}, Abstract = {In this paper we present an implementation of a constraint solving module, CLP(Flex), for dealing with unification in an equality theory for terms with flexible arity function symbols. Then we present an application of CLP(Flex) to XML-processing where XML documents are abstracted by terms with flexible arity symbols. This gives a highly declarative model for XML processing yielding a substantial degree of flexibility in programming.}} @article{Cohen.Kanza.ea_EquiX-asearchand_JASIST_2002, Author = {Cohen, Sara and Kanza, Yaron and Kogan, Yakov and Sagiv, Yehoshua and Nutt, Werner and Serebrenik, Alexander}, Doi = {http://dx.doi.org/10.1002/asi.10058}, Issn = {1532-2882}, Journal = {Journal of the American Society for Information Science and Technology}, Journal-Abbr = {JASIST}, Keywords = {XML query languages searching search engine metadata visual query languages}, Number = {6}, Pages = {454--466}, Pdf = {QueryEvaluation/XML/Cohen.Kanza.ea_EquiX-asearchand_JASIST_2002.pdf}, Publisher = {John Wiley \& Sons, Inc.}, Title = {{EquiX---a search and query language for XML}}, Url = {http://arxiv.org/abs/cs.DB/0110044}, Volume = {53}, Year = {2002}, Abstract = {EquiX is a search language for XML that combines the power of querying with the simplicity of searching. Requirements for such languages are discussed, and it is shown that EquiX meets the necessary criteria. Both a graph-based abstract syntax and a formal concrete syntax are presented for EquiX queries. In addition, the semantics is defined and an evaluation algorithm is presented. The evaluation algorithm is polynomial under combined complexity. EquiX combines pattern matching, quantification, and logical expressions to query both the data and meta-data of XML documents. The result of a query in EquiX is a set of XML documents. A DTD describing the result documents is derived automatically from the query.}} @inproceedings{Cohen.Mamou.ea_XSEarch-SemanticSearch_VLDB_2003, Author = {Cohen, Sara and Mamou, Jonathan and Kanza, Yaron and Sagiv, Yehoshua}, Booktitle = VLDB, Conference-Abbr = {VLDB}, Keywords = {XML IR information retrieval query languages}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/InformationRetrieval/Languages/Cohen.Mamou.ea_XSEarch-SemanticSearch_VLDB_2003.pdf}, Title = {{XSEarch: A Semantic Search Engine for XML}}, Url = {Cohen.Mamou.ea_XSEarch-SemanticSearch_VLDB_2003}, Year = {2003}, Abstract = {XSEarch, a semantic search engine for XML, is presented. XSEarch has a simple query language, suitable for a naive user. It returns semantically related document fragments that satisfy the user's query. Query answers are ranked using extended information-retrieval techniques and are generated in an order similar to the ranking. Advanced indexing techniques were developed to facilitate efficient implementation of XSEarch. The performance of the different techniques as well as the recall and the precision were measured experimentally. These experiments indicate that XSEarch is efficient, scalable and ranks quality results highly.}} @article{Comai.Damiani.ea_ComputingGraphicalQueries_TOIS_2001, Author = {Comai, Sara and Damiani, Ernesto and Fraternali, Piero}, Doi = {http://doi.acm.org/10.1145/502795.502797}, Issn = {1046-8188}, Journal = {ACM Transactions on Information Systems}, Journal-Abbr = {TOIS}, Keywords = {XML query languages visual query languages XML-GL visualization}, Number = {4}, Pages = {371--430}, Pdf = {QueryEvaluation/XML/Comai.Damiani.ea_ComputingGraphicalQueries_TOIS_2001.pdf}, Publisher = {ACM Press}, Title = {{Computing Graphical Queries over XML Data}}, Url = {http://www.elet.polimi.it/upload/comai/Paper/TODS-Xmlgl.pdf}, Volume = {19}, Year = {2001}, Abstract = {The rapid evolution of XML from a mere data exchange format to a universal syntax for encoding domain-specific information raises the need for new query languages specifically conceived to address the characteristics of XML. Such languages should be able not only to extract information from XML documents, but also to apply powerful transformation and restructuring operators, based on a well-defined semantics. Moreover, XML queries should be natural to write and understand, as nontechnical persons also are expected to access the large XML information bases supporting their businesses. This article describes XML-GL, a graphical query language for XML data. XML-GL's uniqueness is in the definition of a graph-based syntax to express a wide variety of XML queries, ranging from simple selections to expressive data transformations involving grouping, aggregation, and arithmetic calculations. XML-GL has an operational semantics based on the notion of graph matching, which serves as a guideline both for the implementation of native processors, and for the adoption of XML-GL as a front-end to any of the XML query languages that are presently under discussion as the standard paradigm for querying XML data.}} @inproceedings{Comai.Marrara.ea_XMLDocumentSummarization_DEXA_2004, Author = {Comai, Sara and Marrara, Stefania and Tanca, Letizia}, Booktitle = {Proc. Intl. Workshop on Database and Expert Systems Applications}, Conference-Abbr = {DEXA}, Keywords = {XML XQuery synopsis query languages}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/XQuery/Comai.Marrara.ea_XMLDocumentSummarization_DEXA_2004.pdf}, Title = {{XML Document Summarization: Using XQuery for Synopsis Creation}}, Year = {2004}, Abstract = {This work presents a methodology to support approximate queries over massive and heterogeneous XML data sets, based on concise data statistics such as histograms or other statistical techniques. The basic idea for approximate answers is to store precomputed summaries of the XML data, also called synopses, and to query them instead of the original database, thus saving time and computational costs. In particular, We concentrate on a set of XQuery transformation rules for the construction of the synopses collection and for querying the synopsis.}} @inproceedings{Conforti.Ghelli.ea_QueryLanguageTQL_WebDB_2002, Author = {Conforti, Giovanni and Ghelli, Giorgio and Albano, Antonio and Colazzo, Dario and Manghi, Paolo and Sartiani, Carlo}, Booktitle = {Proc. Intl. Workshop on the Web and Databases}, Conference-Abbr = {WebDB}, Keywords = {XML query languages TQL ambient logic patterns paths}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/LogicProgrammingApproaches/Conforti.Ghelli.ea_QueryLanguageTQL_WebDB_2002.pdf}, Title = {{The Query Language TQL}}, Url = {http://www.db.ucsd.edu/webdb2002/papers/43.pdf}, Year = {2002}, Abstract = {This work presents the query language TQL, a query language for semistructured data, that can be used to query XML files. TQL substitutes the standard path-based pattern-matching mechanism with a logic-based mechanism, where the programmer specifies the properties of the pieces of data she is trying to extract. As a result, TQL queries are more ?declarative?, or less ?operational?, than queries in comparable languages. This feature makes some queries easier to express, and should allow the adoption of better optimization techniques. Through a set of examples, we show that the range of queries that can be declaratively expressed in TQL is quite wide. The implementation of TQL binding mechanism requires the adoption of non-standard techniques, and some of its aspects are still open. In this paper we implicitly report about the current status of the implementation by writing all queries using the version of TQL that has been implemented, and that can be freely downloaded from //tql.di.unipi.it/tql.}} @techreport{Cowan.Tobin_XMLInformationSet_TR_2004, Author = {Cowan, John and Tobin, Richard}, Institution = {W3C}, Keywords = {XML Infoset W3C data model}, Owner = {Tim Furche}, Title = {{XML Information Set (2nd Ed.)}}, Type = {Recommendation}, Url = {http://www.w3.org/TR/xml-infoset/}, Urldate = {2005/01/31}, Year = {2004}, Abstract = {This specification provides a set of definitions for use in other specifications that need to refer to the information in an XML document.}} @inproceedings{DeHaan.Toman.ea_ComprehensiveXQueryto_SIGMOD_2003, Author = {DeHaan, David and Toman, David and Consens, Mariano P. and {\"O}zsu, M. Tamer}, Booktitle = SIGMOD, Conference-Abbr = {SIGMOD}, Doi = {http://doi.acm.org/10.1145/872757.872832}, Isbn = {1-58113-634-X}, Keywords = {XML XQuery relational implementation tree encoding dynamic interval encoding}, Location = {San Diego, California}, Pages = {623--634}, Pdf = {QueryEvaluation/XML/XQuery/DeHaan.Toman.ea_ComprehensiveXQueryto_SIGMOD_2003.pdf}, Publisher = {ACM Press}, Title = {{A Comprehensive XQuery to SQL Translation using Dynamic Interval Encoding}}, Url = {http://db.uwaterloo.ca/~david/cs848/toman-et-al-sigmod.pdf}, Year = {2003}, Abstract = {The W3C XQuery language recommendation, based on a hierarchical and ordered document model, supports a wide variety of constructs and use cases. There is a diversity of approaches and strategies for evaluating XQuery expressions, in many cases only dealing with limited subsets of the language. In this paper we describe an implementation approach that handles XQuery with arbitrarily-nested FLWR expressions, element constructors and built-in functions (including structural comparisons). Our proposal maps an XQuery expression to a single equivalent SQL query using a novel dynamic interval encoding of a collection of XML documents as relations, augmented with information tied to the query evaluation environment. The dynamic interval technique enables (suitably enhanced) relational engines to produce predictably good query plans that do not preclude the use of sort-merge join query operators. The benefits are realized despite the challenges presented by intermediate results that create arbitrary documents and the need to preserve document order as prescribed by semantics of XQuery. Finally, our experimental results demonstrate that (native or relational) XML systems can benefit from the above technique to avoid a quadratic scale up penalty that effectively prevents the evaluation of nested FLWR expressions for large documents.}} @techreport{DeRoseMaier.XML-Linking-Language.2001, Author = {DeRose, Steve and Maier, Eve and Orchard, David}, Date-Added = {2005-05-01 13:59:00 +0200}, Date-Modified = {2005-09-29 00:29:34 +0200}, Institution = {W3C}, Keywords = {XML XLink linking relations}, Title = {{XML Linking Language (XLink) Version 1.0}}, Type = {Recommendation}, Url = {http://www.w3.org/TR/xlink/}, Year = {2001}} @inproceedings{Deutsch.Fernandez.ea_QueryLanguageXML_WWW_1999, Author = {Deutsch, Alin and Fernandez, Mary and Florescu, Daniela and Levy, Alon and Suciu, Dan}, Booktitle = WWW, Conference-Abbr = {WWW}, Keywords = {XML query languages XML-QL pattern}, Owner = {Tim Furche}, Title = {{A Query Language for XML}}, Url = {http://www.research.att.com/~mff/xmlql/doc/files/final.html}, Year = {1999}, Abstract = {An important application of XML is the interchange of electronic data (EDI) between multiple data sources on the Web. As XML data proliferates on the Web, applications will need to integrate and aggregate data from multiple source and clean and transform data to facilitate exchange. Data extraction, conversion, transformation, and integration are all well-understood database problems, and their solutions rely on a query language. We present a query language for XML, called XML-QL, which we argue is suitable for performing the above tasks. XML-QL is a declarative, ``relational complete'' query language and is simple enough that it can be optimized. XML-QL can extract data from existing XML documents and construct new XML documents.}} @inproceedings{Deutsch.Fernandez.ea_XML-QL-QueryLanguage_QL98_1998, Author = {Deutsch, Alin and Fernandez, Mary and Florescu, Daniela and Levy, Alon and Suciu, Dan}, Booktitle = PROC # {W3C QL'98 -- Query Languages 1998}, Conference-Abbr = {QL98}, Howpublished = {Note}, Institution = {W3C}, Keywords = {XML XML-QL query languages positional}, Organization = {W3C}, Title = {{XML-QL: A Query Language for XML}}, Url = {http://www.w3.org/TR/1998/NOTE-xml-ql-19980819/}, Year = {1998}} @inproceedings{Deutsch.Papakonstantinou.ea_NEXTLogicalFramework_VLDB_2004, Author = {Deutsch, Alin and Papakonstantinou, Yannis and Xu, Yu}, Booktitle = VLDB, Conference-Abbr = {VLDB}, Keywords = {XML XQuery optimization logical query optimization rewriting}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/XQuery/Deutsch.Papakonstantinou.ea_NEXTLogicalFramework_VLDB_2004.pdf}, Title = {{The NEXT Logical Framework for XQuery}}, Url = {http://www.vldb.org/conf/2004/RS4P5.PDF}, Year = {2004}, Abstract = {Classical logical optimization techniques rely on a logical semantics of the query language. The adaptation of these techniques to XQuery is precluded by its definition as a functional language with operational semantics. We introduce Nested XML Tableaux which enable a logical foundation for XQuery semantics and provide the logical plan optimization framework of our XQuery processor. As a proof of concept, we develop and evaluate a minimization algorithm for removing redundant navigation within and across nested subqueries. The rich XQuery features create key challenges that fundamentally extend the prior work on the problems of minimizing conjunctive and tree pattern queries.}} @inproceedings{Deutsch.Tannen_ContainmentandIntegrity_KRDB_2001, Author = {Deutsch, Alin and Tannen, Val}, Booktitle = {Proc. Intl. Workshop on Knowledge Representation meets Databases}, Conference-Abbr = {KRDB}, Keywords = {XML XPath query containment fragments query languages}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/PathExpressions/XPath/Deutsch.Tannen_ContainmentandIntegrity_KRDB_2001.pdf}, Title = {{Containment and Integrity Constraints for XPath Fragments}}, Url = {http://ceur-ws.org/Vol-45/01-deutsch.ps}, Year = {2001}} @inproceedings{deVos.Rowbotham_KnowledgeRepresentationPower_PICA_2001, Author = {deVos, Arnold and Rowbotham, C. T.}, Booktitle = {IEEE Conference for Power Industry Computer Applications (PICA)}, Conference-Abbr = {PICA}, Keywords = {Application Use Cases RDF}, Owner = {Tim Furche}, Pdf = {SemanticWeb/RDF/Applications/deVos.Rowbotham_KnowledgeRepresentationPower_PICA_2001.pdf}, Title = {{Knowledge Representation for Power System Modelling}}, Url = {http://www.langdale.com.au/PICA/KRforPSM.pdf}, Urldate = {2004/12/20}, Year = {2001}, Abstract = {Modelling power systems is an area of ongoing interest in the transmission management and control systems community. Continuing development is driven by two forces. The traditional tasks of model maintenance and management must be achieved with fewer resources. At the same time, model exchange and coordination has become a priority. The latter force arises from the disaggregation of utility functions and the introduction of power markets. This paper begins by identifying some of the power system modelling tasks that have become important, but are ill served by current tools and techniques. Among these are model versioning and version control, migration of models between different schema, the transformation of models for different purposes or applications, and the merging of models from different sources. These tasks are typically handled by semi-manual methods or heavily customized software. The paper then describes the application of knowledge representation to power system modelling. In particular, the power of this approach to provide generic solutions to the foregoing problems is explored. Knowledge representation is contrasted with more common data representations and put into context with current industry initiatives, EPRI CIM, UMS DAF and XML/CIM. Finally, the feasibility of using knowledge representation for power system models is illustrated with a case study from a major Australian distribution utility.}} @inproceedings{Dolog.Henze.ea_PersonalizationinDistributed_WWW_2004, Author = {Dolog, Peter and Henze, Nicola and Nejdl, Wolfgang and Sintek, Michael}, Booktitle = WWW, Conference-Abbr = {WWW}, Keywords = {Personalization E-Learning Web}, Owner = {Tim Furche}, Pdf = {ApplicationAreas/Personalization/Dolog.Henze.ea_PersonalizationinDistributed_WWW_2004.pdf}, Title = {{Personalization in Distributed e-Learning Environments}}, Url = {http://www.kbs.uni-hannover.de/Arbeiten/Publikationen/2004/dolog_henze_nejdl_sintek_www2004.pdf}, Year = {2004}} @inproceedings{Dolog.Henze.ea_PersonalReader:Personalizing_AH_2004, Author = {Dolog, Peter and Henze, Nicola and Nejdl, Wolfgang and Sintek, Michael}, Booktitle = {Proc. Intl. Conf. on Adaptive Hypermedia and Adaptive Web-Based Systems}, Conference-Abbr = {AH}, Keywords = {Personalization E-Learning Personal Reader Semantic Web RDF}, Owner = {Tim Furche}, Pdf = {ApplicationAreas/Personalization/Dolog.Henze.ea_PersonalReader:Personalizing_AH_2004.pdf}, Title = {{The Personal Reader: Personalizing and Enriching Learning Resources using Semantic Web Technologies}}, Url = {http://www.kbs.uni-hannover.de/Arbeiten/Publikationen/2004/ah2004_d_h_n_s.pdf}, Year = {2004}, Abstract = {Traditional adaptive hypermedia systems have focused on providing adaptation functionality on a closed corpus, while Web search interfaces have delivered non-personalized information to users. In this paper, we show how we integrate closed corpus adaptation and global context provision in a Personal Reader environment. The local context consists of individually optimized recommendations to learning materials within the given corpus; the global context provides individually optimized recommendations to resources found on the Web, e.g., FAQs, student exercises, simulations, etc. The adaptive local context of a learning resource is generated by applying methods from adaptive educational hypermedia in a semantic web setting. The adaptive global context is generated by constructing appropriate queries, enrich them based on available user pro le information, and, if necessary, relax them during the querying process according to available metadata.}} @inproceedings{DomsFurche.How-to-Query-the-Gen.2005, Author = {Doms, Andreas and Furche, Tim and Burger, Albert and Schroeder, Michael}, Booktitle = {Symposium on Knowledge Representation in Bioinformatics (KRBIO'05), Espoo, Finland (17th June 2005)}, Conference-Abbr = {KRBIO}, Date-Added = {2005-04-20 13:40:41 +0200}, Date-Modified = {2006-03-06 17:52:05 +0100}, Keywords = {Xcerpt XML Prolog Bioinformatics GeneOntology Use cases Prova}, Title = {How to Query the GeneOntology}, Url = {http://www.pms.ifi.lmu.de/publikationen#PMS-FB-2005-15}, Year = {2005}} @inproceedings{Dong.Bailey_OptimizationofXML_WISE_2004, Author = {Dong, Ce and Bailey, James}, Booktitle = {Proc. Intl. Conf. on Web Information Systems Engineering}, Conference-Abbr = {WISE}, Keywords = {XML XSLT optimization query languages}, Owner = {Tim Furche}, Title = {{Optimization of XML Transformations Using Template Specialization}}, Year = {2004}} @inproceedings{Dong.Bailey_StaticAnalysisof_ADC_2004, Author = {Dong, Ce and Bailey, James}, Booktitle = {Proc. Australasian Database Conf.}, Conference-Abbr = {ADC}, Isbn = {1-111-11111-1}, Keywords = {XML XSLT error checking typing query languages}, Location = {Dunedin, New Zealand}, Pages = {151--160}, Pdf = {QueryEvaluation/XML/XSLT/Dong.Bailey_StaticAnalysisof_ADC_2004.pdf}, Publisher = {Australian Computer Society, Inc.}, Title = {{Static Analysis of XSLT Programs}}, Url = {http://www.cs.mu.oz.au/~jbailey/papers/adc.pdf}, Year = {2004}, Abstract = {XML is becoming the dominant standard for representing and exchanging data on the World Wide Web. The ability to transform and present data in XML is crucial and XSLT (Extensible Stylesheet Language Transformations) is the principal programming language that supports this activity. Methods for analysis of XSLT programs are currently an important open issue. In this paper, we discuss new methods for analysing XSLT programs, which return information about reachability, invalid calling relationships and termination properties. Our methods are based on the determination of the associations which can exist between components of an XSLT program, refined by the knowledge from a DTD. Such analysis is important for debugging and verification of XSLT programs and also their optimisation.}} @techreport{Draper.Frankhauser.ea_XQuery1.0and_TR_2005, Author = {Draper, Denise and Frankhauser, Peter and Fern{\'a}ndez, Mary and Malhotra, Ashok and Rose, Kristoffer and Rys, Michael and Sim{\'e}on, J{\'e}r{\^o}me and Wadler, Philip}, Institution = {W3C}, Keywords = {XML XQuery Use Cases W3C Query Query Languages}, Owner = {Tim Furche}, Title = {{XQuery 1.0 and XPath 2.0 Formal Semantics}}, Type = {Working Draft}, Url = {http://www.w3.org/TR/xquery-semantics/}, Urldate = {2005/01/31}, Year = {2005}, Abstract = {This document defines formally the semantics of XQuery 1.0 [XQuery 1.0: A Query Language for XML] and XPath 2.0 [XML Path Language (XPath) 2.0].}} @article{Eisenberg.Melton_earlyLookat_SIGMOD_2004, Author = {Eisenberg, Andrew and Melton, Jim}, Doi = {http://doi.acm.org/10.1145/1024694.1024717}, Issn = {0163-5808}, Journal = {SIGMOD Record}, Journal-Abbr = {SIGMOD}, Keywords = {XML XQuery Java XQJ API query languages}, Number = {2}, Pages = {105--111}, Pdf = {QueryEvaluation/XML/XQuery/Eisenberg.Melton_earlyLookat_SIGMOD_2004.pdf}, Publisher = {ACM Press}, Title = {{An early Look at XQuery API for Java\texttrademark (XQJ)}}, Url = {http://portal.acm.org/citation.cfm?id=1024694.1024717}, Volume = {33}, Year = {2004}, Abstract = {In Feb. 2004, the period for submitting Last Call Working Draft comments for most parts of the XQuery specification came to a close. While there is still a great deal of work to be done to make XQuery a W3C Recommendation, the documents have become more stable with each public release. In this column we'd like to provide an initial look at the XQuery API for Java? (XQJ), a project that is taking place within the Java Community Process (JCP).}} @article{Eisenberg.Melton_earlyLookat_SIGMOD_2002, Author = {Eisenberg, Andrew and Melton, Jim}, Doi = {http://doi.acm.org/10.1145/637411.637433}, Issn = {0163-5808}, Journal = {SIGMOD Record}, Journal-Abbr = {SIGMOD}, Keywords = {XML XQuery query languages historical}, Number = {4}, Pages = {113--120}, Pdf = {QueryEvaluation/XML/XQuery/Eisenberg.Melton_earlyLookat_SIGMOD_2002.pdf}, Publisher = {ACM Press}, Title = {{An early Look at XQuery}}, Url = {http://portal.acm.org/citation.cfm?id=637433}, Volume = {31}, Year = {2002}} @inproceedings{Eiter.Ianni.ea_NonmonotonicDescriptionLogic_LPAR_2005, Author = {Eiter, Thomas and Ianni, Giovambattista and Schindlauer, Roman and Tompits, Hans}, Booktitle = LPAR, Conference-Abbr = {LPAR}, Keywords = {Description Logics Evaluation Semantic Web REWERSE}, Owner = {Tim Furche}, Publisher = {Springer-Verlag}, Series = {LNCS}, Title = {{Nonmonotonic Description Logic Programs: Implementation and Experiments}}, Year = {2005}} @inproceedings{Eiter.Lukasiewicz.ea_CombiningAnswerSet_KR_2004, Author = {Eiter, Thomas and Lukasiewicz, Thomas and Schindlauer, Roman and Tompits, Hans}, Booktitle = {Proc. Principles of Knowledge Representation and Reasoning (KR)}, Conference-Abbr = {KR}, Keywords = {Semantic Web Description Logics Answer-set Programming Query Languages Reasoning REWERSE}, Owner = {Tim Furche}, Pages = {141--151}, Pdf = {QueryEvaluation/SemanticWeb/Eiter.Lukasiewicz.ea_CombiningAnswerSet_KR_2004.pdf}, Title = {{Combining Answer Set Programming with Description Logics for the Semantic Web}}, Url = {http://www.kr.tuwien.ac.at/staff/tompits/papers/kr-04-coupling.pdf}, Urldate = {2005/01/28}, Year = {2004}, Abstract = {Towards the integration of rules and ontologies in the Semantic Web, we propose a combination of logic programming under the answer set semantics with the description logics SHIF(D) and SHOIN(D), which underly the Web ontology languages OWL Lite and OWL DL, respectively. This combination allows for building rules on top of ontologies but also, to a limited extent, building ontologies on top of rules. We introduce description logic programs (dl-programs), which consist of a description logic knowledge base L and a finite set of description logic rules (dl-rules) P. Such rules are similar to usual rules in logic programs with negation as failure, but may also contain queries to L, possibly default negated, in their bodies. We define Herbrand models for dl-programs, and show that satisfiable positive dl-programs have a unique least Herbrand model. More generally, consistent stratified dlprograms can be associated with a unique minimal Herbrand model that is characterized through iterative least Herbrand models. We then generalize the (unique) minimal Herbrand model semantics for positive and strati- fied dl-programs to a strong answer set semantics for all dl-programs, which is based on a reduction to the least model semantics of positive dl-programs. We also de- fine a weak answer set semantics based on a reduction to the answer sets of ordinary logic programs. Strong answer sets are weak answer sets, and both properly generalize answer sets of ordinary normal logic programs. We then give fixpoint characterizations for the (unique) minimal Herbrand model semantics of positive and stratified dl-programs, and show how to compute these models by finite fixpoint iterations. Furthermore, we give a precise picture of the complexity of deciding strong and weak answer set existence for a dl-program.}} @inproceedings{Eiter.Lukasiewicz.ea_Well-foundedSemanticsDescription_RuleML_2004, Author = {Eiter, Thomas and Lukasiewicz, Thomas and Schindlauer, Roman and Tompits, Hans}, Booktitle = {Proc. RuleML Workshop, ISWC}, Conference-Abbr = {RuleML}, Keywords = {Semantic Web Description Logics Semantics Querying REWERSE}, Owner = {Tim Furche}, Pages = {81--97}, Pdf = {QueryEvaluation/SemanticWeb/Eiter.Lukasiewicz.ea_Well-foundedSemanticsDescription_RuleML_2004.pdf}, Publisher = {Springer-Verlag}, Series = {LNCS}, Title = {{Well-founded Semantics for Description Logic Programs in the Semantic Web}}, Url = {http://www.kr.tuwien.ac.at/staff/lukasiew/ruleml04.pdf}, Urldate = {2005/01/28}, Volume = {3323}, Year = {2004}, Abstract = {In previous work, towards the integration of rules and ontologies in the SemanticWeb, we have proposed a combination of logic programming under the answer set semantics with the description logics SHIF(D) and SHOIN(D), which underly the Web ontology languages OWL Lite and OWL DL, respectively. More precisely, we have introduced description logic programs (or dl-programs), which consist of a description logic knowledge base L and a nite set of description logic rules P, and we have de ned their answer set semantics. In this paper, we continue this line of research. Here, as a central contribution, we present the well-founded semantics for dl-programs, and we analyze its semantic properties. In particular, we show that it generalizes the well-founded semantics for ordinary normal programs. Furthermore, we show that in the general case, the well-founded semantics of dl-programs is a partial model that approximates the answer set semantics, whereas in the positive and the stratified case, it is a total model that coincides with the answer set semantics. Finally, we also provide complexity results for dl-programs under the well-founded semantics.}} @article{Fankhauser_XQueryFormalSemantics_SIGMOD_2001, Author = {Fankhauser, Peter}, Doi = {http://doi.acm.org/10.1145/603867.603870}, Issn = {0163-5808}, Journal = {SIGMOD Record}, Journal-Abbr = {SIGMOD}, Keywords = {XML XQuery formal semantics historical query languages}, Number = {3}, Pages = {14--19}, Pdf = {QueryEvaluation/XML/XQuery/Fankhauser_XQueryFormalSemantics_SIGMOD_2001.pdf}, Publisher = {ACM Press}, Title = {{XQuery Formal Semantics: State and Challenges}}, Url = {http://portal.acm.org/citation.cfm?id=603870}, Volume = {30}, Year = {2001}, Abstract = {The XQuery formalization is an ongoing effort of the W3C XML Query working group to define a precise formal semantics for XQuery. This paper briefly introduces the current state of the formalization and discusses some of the more demanding remaining challenges in formally describing an expressive query language for XML.}} @inproceedings{Fankhauser_XQuerybybook_XML_2002, Author = {Fankhauser, Peter and Lehti, Patrick}, Booktitle = {XML Conference \& Exhibition}, Conference-Abbr = {XML}, Keywords = {XML XQuery implementation experience query languages}, Owner = {Tim Furche}, Title = {{XQuery by the book: The IPSI XQuery Demonstrator}}, Url = {http://www.ipsi.fraunhofer.de/oasys/projects/ipsi-xq/XQuery%20by%20the%20book.rtf}, Year = {2002}, Abstract = {XQuery is being developed by the W3C XML Query working group as a standard query language for XML. It is a fully compositional, strongly typed functional language to flexibly select, recombine, and restructure XML documents and fragments. This paper introduces IPSI-XQ, a comprehensive implementation of XQuery "by the book", which closely follows XQuery's formal semantics, realizing all steps of the abstract XQuery processing model in an open and modular way to arrive at a fully conformant, type safe implementation. It describes how the formal specification can be deployed for type analysis and query optimization, and discusses the pros and cons of the approach.}} @techreport{Fernandez.Malhotra.ea_XQuery1.0and_TR_2005, Author = {Fern{\'a}ndez, Mary and Malhotra, Ashok and Marsh, Jonathan and Nagy, Marton and Walsh, Norman}, Institution = {W3C}, Keywords = {XML XQuery XPath data model query languages}, Owner = {Tim Furche}, Title = {{XQuery 1.0 and XPath 2.0 Data Model}}, Type = {Working Draft}, Url = {http://www.w3.org/TR/xpath-datamodel/}, Urldate = {2005/01/31}, Year = {2005}, Abstract = {This document defines the W3C XQuery 1.0 and XPath 2.0 Data Model, which is the data model of [XPath 2.0], [XSLT 2.0], and [XQuery], and any other specifications that reference it. This data model is based on the [XPath 1.0] data model and earlier work on an [XML Query Data Model]. This document is the result of joint work by the [XSL Working Group] and the [XML Query Working Group].}} @inproceedings{Fernandez.Simeon.ea_ImplementingXQuery1.0_VLDB_2003, Author = {Fern{\'a}ndez, Mary and Sim{\'e}on, J{\'e}r{\^o}me and Choi, Byron and Marian, Am{\'e}lie and Sur, Gargi}, Booktitle = VLDB, Conference-Abbr = {VLDB}, Keywords = {XML XQuery galax implementation query languages}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/XQuery/Fernandez.Simeon.ea_ImplementingXQuery1.0_VLDB_2003.pdf}, Title = {{Implementing XQuery 1.0 : The Galax Experience}}, Url = {http://www.vldb.org/conf/2003/papers/S35P07.pdf}, Year = {2003}, Abstract = {Galax is a light-weight, portable, open-source implementation of XQuery 1.0. Started in December 2000 as a small prototype designed to test the XQuery static type system, Galax has now become a solid implementation, aiming at full conformance with the family of XQuery 1.0 specifi- cations. Because of its completeness and open architecture, Galax also turns out to be a very convenient platform for researchers interested in experimenting with XQuery optimization. We demonstrate the Galax system as well as its most advanced features, including support for XPath 2.0, XML Schema and static typechecking. We also present some of our first experiments with optimization. Notably, we demonstrate query rewriting capabilities in the Galax compiler, and the ability to run queries on documents up to a Gigabyte without the need for preindexing. Although early versions of Galax have been shown in industrial conferences over the last two years, this is the first time it is demonstrated in the database community.}} @inproceedings{Florescu.Fernandez.ea_QueryLanguageand_WMSD_1997, Author = {Florescu, Daniela and Fernandez, Mary and Levy, Alon and Suciu, Dan}, Booktitle = {Proc. Workshop on Management of Semi-structured Data}, Conference-Abbr = {WMSD}, Keywords = {XML query languages StruQL navigational path expression}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/Languages/Florescu.Fernandez.ea_QueryLanguageand_WMSD_1997.pdf}, Title = {{A Query Language and Processor for a Web-site Management System}}, Url = {http://www.research.att.com/~mff/strudel/doc/files/workshop97.ps.gz}, Year = {1997}} @article{Florescu.Hillery.ea_BEAstreamingXQuery_VLDBJ_2004, Author = {Florescu, Daniela and Hillery, Chris and Kossmann, Donald and Lucas, Paul and Riccardi, Fabio and Westmann, Till and Carey, Michael J. and Sundararajan, Arvind}, Doi = {http://dx.doi.org/10.1007/s00778-004-0137-1}, Issn = {1066-8888}, Journal = {VLDB Journal}, Journal-Abbr = {VLDBJ}, Keywords = {XML XQuery query processing implementation query languages}, Number = {3}, Pages = {294--315}, Pdf = {QueryEvaluation/XML/XQuery/Florescu.Hillery.ea_BEAstreamingXQuery_VLDBJ_2004.pdf}, Publisher = {Springer-Verlag New York, Inc.}, Title = {{The BEA Streaming XQuery Processor}}, Url = {http://www-dbs.informatik.uni-heidelberg.de/publications/vldbj.pdf}, Volume = {13}, Year = {2004}, Abstract = {This paper describes the design, implementation, and performance characteristics of a commercial XQuery processing engine, the BEA streaming XQuery processor. This XQuery engine was designed to provide high performance for message-processing applications, i.e., for transforming XML data streams. The engine is a central component of the 8.1 release of BEA?s WebLogic Integration (WLI) product. The BEA XQuery engine is fully compliant with the August 2002 draft of the W3C XML Query Language specification and we are currently porting it to the latest version of the XQuery language (July 2004). A goal of this paper is to describe how a fully compliant yet efficient XQuery engine has been built from a few relatively simple components and well-understood technologies.}} @article{Florescu.Levy.ea_QueryLanguageWeb-site_SIGMOD_1997, Author = {Florescu, Daniela and Levy, Alon and Fernandez, Mary and Suciu, Dan}, Booktitle = {SIGMOD}, Conference-Abbr = {WMSD}, Journal = {SIGMOD Record}, Journal-Abbr = {SIGMOD}, Keywords = {XML query languages StruQL navigational path expression}, Number = {3}, Owner = {Tim Furche}, Pages = {4--11}, Pdf = {QueryEvaluation/Languages/Florescu.Fernandez.ea_QueryLanguageand_WMSD_1997.pdf}, Title = {{A Query Language for a Web-site Management System}}, Url = {http://www.research.att.com/~mff/strudel/doc/files/sigmodrec97.ps.gz}, Volume = {26}, Year = {1997}} @talk{Furche_BusinessRulesConference_SLIDES_2004, Author = {Furche, Tim}, Institution = {Institute for Computer Science, University of Munich, Germany}, Keywords = {Semantic Web Use Cases Business Rules}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/Streams/XPath/Furche_QueryOptimizationon_SLIDES_2003.pdf}, Title = {{Business Rules Conference 2004: Report and Experiences}}, Type = {Oberseminar ?Knowledge Representation and Markup Languages?}, Year = {2004}} @talk{Furche_XcerptandXChange_SLIDES_2004, Author = {Furche, Tim}, Institution = {Institute for Computer Science, University of Munich, Germany}, Keywords = {Semantic Web Use Cases Bioinformatics Application}, Owner = {Tim Furche}, Pdf = {ApplicationAreas/Bioinformatics/Furche_XcerptandXChange_SLIDES_2004.pdf}, Title = {{Xcerpt and XChange in Bioinformatics}}, Type = {Oberseminar ?Knowledge Representation and Markup Languages?}, Year = {2004}, Abstract = {Collaboration and Use Cases}} @mastersthesis{Furche_OptimizingMultipleQueries_2003, Address = {6}, Author = {Furche, Tim}, Keywords = {Query Evaluation Streams XPath XML}, Pdf = {QueryEvaluation/Streams/XPath/Furche_OptimizingMultipleQueries_2003.pdf}, School = {Institute of Computer Science, University of Munich, Germany}, Title = {{Optimizing Multiple Queries against XML Streams}}, Type = {Diplomarbeit}, Url = {http://www.pms.ifi.lmu.de/publikationen/#DA_Tim.Furche}, Urldate = {2004/11/11}, Year = {2003}, Abstract = {Processing and querying streams, XML streams in particular, has recently become a widely recognized area of interest both in research and in industry. In contrast to traditional query evaluation for databases, where multiple queries against the same data can be evaluated sequentially, for a streamed environment only the simultaneous execution of multiple queries is feasible, as the sequential evaluation requires multiple passes over the stream. This work presents an overview of techniques for optimizing multiple queries posed against a stream of XML data. Building upon the SPEX query engine [Kiesling, Master Thesis, 2002; Olteanu et al., ICDE, 2003], the problem how to find a cost-optimal query plan that allows the simultaneous evaluation of multiple queries against the same stream is presented and shown to be not only hard to solve but also hard to approximate, if arbitrary parts, and not only common prefixes as in previous approaches, can be shared among query plans. Several heuristics are investigated and compared, in particular with respect to their complexity. Furthermore, it is shown how to extend the SPEX query engine to support such query plans for multiple queries. This extension proves to be both natural and efficient. An extensive experimental evaluation shows that sharing arbitrary operators under a realistic cost function results in query plans that have consistently lower cost for reasonable sets of queries than query plans where only common prefixes are considered. In most cases, the relative improvement is higher than 50%. Although the time for generating such query plans is higher than for query plans where only common prefixes are shared, the increase in time is within an acceptable margin.}} @talk{Furche_QueryOptimizationon_SLIDES_2003, Author = {Furche, Tim}, Institution = {Institute for Computer Science, University of Munich, Germany}, Keywords = {Path Expressions Query Evaluation Streams XML Presentation}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/Streams/XPath/Furche_QueryOptimizationon_SLIDES_2003.pdf}, Title = {{Query Optimization on XML Streams}}, Type = {Oberseminar ?Knowledge Representation and Markup Languages?}, Year = {2003}, Abstract = {Techniques for multi-query optimization in face of semi-structured streams}} @talk{Furche_QueryMergingXML_SLIDES_2002, Author = {Furche, Tim}, Institution = {Institute for Computer Science, University of Munich, Germany}, Keywords = {Path Expressions Query Evaluation Streams XML Presentation}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/Streams/XPath/Furche_QueryOptimizationon_SLIDES_2003.pdf}, Title = {{Query Merging for XML Streams}}, Type = {Oberseminar ?Knowledge Representation and Markup Languages?}, Year = {2002}, Abstract = {Overview of techniques for multi-query optimization in the SPEX framework}} @techreport{Furche.Bry.ea_SurveyoverExisting_TR_2004, Author = {Furche, Tim and Bry, Fran{\c c}ois and Schaffert, Sebastian and Orsini, Renzo and Horrocks, Ian and Krauss, Michael and Bolzer, Oliver}, Date-Modified = {2006-03-06 17:45:17 +0100}, Editor = {Tim Furche}, Institution = {REWERSE}, Keywords = {REWERSE Survey Query Languages RDF XML}, Number = {I4-D1}, Pdf = {QueryEvaluation/SemanticWeb/Furche.Bry.ea_SurveyoverExisting_TR_2004.pdf}, Title = {{Survey over Existing Query and Transformation Languages}}, Type = {Deliverable}, Url = {http://rewerse.net/publications.html#REWERSE-DEL-2004-I4-D1}, Urldate = {2004/11/11}, Year = {2004}, Abstract = {A widely acknowledged obstacles for realizing the vision of the Semantic Web is the inability of many current Semantic Web approaches to cope with data available in such diverging representation formalisms as XML, RDF, or Topic Maps. A common query language is the first step to allow transparent access to data in any of these formats. To further the understanding of the requirements and approaches proposed for query languages in the conventional as well as the Semantic Web, this report surveys a large number of query languages for accessing XML, RDF, or Topic Maps. This is the first systematic survey to consider query languages from all these areas. From the detailed survey of these query languages, a common classification scheme is derived that is useful for understanding and di erentiating languages within and among all three areas.}} @talk{Furche.Hoehler.ea_Probablybetter..._SLIDES_2002, Author = {Furche, Tim and H{\"o}hler, Thomas and Weigel, Felix}, Institution = {University of Tilburg, Netherlands, the University of T{\"u}bingen, Germany, and the Centre for Information and Language Processing, Munich, Germany, at Blaubeuren, Germany}, Keywords = {Path Expressions Query Evaluation Streams XML Presentation}, Owner = {Tim Furche}, Title = {{Probably better ..., Looking at Probabilistic and Non-Probabilistic Indexing}}, Type = {Presentation at the Fourth Virtugrade meeting on ?Information Retrieval?}, Year = {2002}} @talk{Furche.Patranjan_XcerptandXChange_SLIDES_2004, Author = {Furche, Tim and P{\u a}tr{\^a}njan, Paula-Lavinia}, Date-Modified = {2005-04-29 22:11:30 +0200}, Institution = {REWERSE Working Group ``Adding Semantics to the Bioinformatics Web''}, Keywords = {Design Query Languages Xcerpt Presentation REWERSE}, Location = {Dresden, Germany}, Owner = {Tim Furche}, Pdf = {SemanticWeb/Xcerpt/Furche.Patranjan_XcerptandXChange_SLIDES_2004.pdf}, Title = {{Xcerpt and XChange: Combining Querying, Reasoning and Reactivity}}, Type = {Internal Workshop}, Year = {2004}} @inproceedings{Groppe.Boettcher_XPathQueryTransformation_WIDM_2003, Author = {Groppe, Sven and B{\"o}ttcher, Stefan}, Booktitle = {Proc. Intl. Workshop on Web Information and Data Management}, Conference-Abbr = {WIDM}, Doi = {http://doi.acm.org/10.1145/956699.956723}, Isbn = {1-58113-725-7}, Keywords = {XML XSLT query optimization rewriting}, Location = {New Orleans, Louisiana, USA}, Pages = {106--110}, Pdf = {QueryEvaluation/XML/XSLT/Groppe.Boettcher_XPathQueryTransformation_WIDM_2003.pdf}, Publisher = {ACM Press}, Title = {{XPath Query Transformation based on XSLT Stylesheets}}, Url = {http://portal.acm.org/citation.cfm?id=956723}, Year = {2003}, Abstract = {Whenever XML data must be shared by heterogeneous applications, transformations between different application-specific XML formats are necessary. The state-of-the-art method transforms entire XML documents from one application format into another e.g. by using an XSLT stylesheet, so that each application can work locally on its preferred format. In our approach, we use an XSLT stylesheet in order to transform a given XPath query such that we retrieve and transform only that part of the XML document which is sufficient to answer the given query. Among other things, our approach avoids problems of replication, saves processing time and in distributed scenarios, transportation costs.}} @inproceedings{Grust_AcceleratingXPathLocation_SIGMOD_2002, Author = {Grust, Thorsten}, Booktitle = SIGMOD, Conference-Abbr = {SIGMOD}, Keywords = {XML XPath relational implementation location steps efficiency accelerating}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/XQuery/Grust_AcceleratingXPathLocation_VLDB_2003.pdf}, Title = {{Accelerating XPath Location Steps}}, Url = {http://www.in.tu-clausthal.de/~grust/files/xpath-accel.pdf}, Year = {2002}, Abstract = {This work is a proposal for a database index structure that has been speci cally designed to support the evaluation of XPath queries. As such, the index is capable to support all XPath axes (including ancestor, following, precedingsibling, descendant-or-self, etc.). This feature lets the index stand out among related work on XML indexing structures which had a focus on regular path expressions (which correspond to the XPath axes children and descendantor- self plus name tests). Its ability to start traversals from arbitrary context nodes in an XML document additionally enables the index to support the evaluation of path traversals embedded in XQuery expressions. Despite its exibility, the new index can be implemented and queried using purely relational techniques, but it performs especially well if the underlying database host provides support for R-trees. A performance assessment which shows quite promising results completes this proposal.}} @inproceedings{Grust.Sakr.ea_XQueryonSQL_VLDB_2004, Author = {Grust, Torsten and Sakr, Sherif and Teubner, Jens}, Booktitle = VLDB, Conference-Abbr = {VLDB}, Keywords = {XML XQuery relational implementation SQL}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/XQuery/Grust.Sakr.ea_XQueryonSQL_VLDB_2004.pdf}, Title = {{XQuery on SQL Hosts}}, Url = {http://www.in.tu-clausthal.de/~grust/files/sql-mapping.pdf}, Year = {2004}, Abstract = {Relational database systems may be turned into efficient XML and XPath processors if the system is provided with a suitable relational tree encoding. This paper extends this relational XML processing stack and shows that an RDBMS can also serve as a highly efficient XQuery runtime environment. Our approach is purely relational: XQuery expressions are compiled into SQL code which operates on the tree encoding. The core of the compilation procedure trades XQuery's notions of variable scopes and nested iteration (FLWOR blocks) for equi-joins. The resulting relational XQuery processor closely adheres to the language semantics, e.g., it obeys node identity as well as document and sequence order, and can support XQuery's full axis feature. The system exhibits quite promising performance figures in experiments. Somewhat unexpectedly, we will also see that the XQuery compiler can make good use of SQL's OLAP functionality.}} @inproceedings{Guizzardi.Wagner.ea_OntologicallyWell-FoundedProfile_CAiSE_2004, Author = {Guizzardi, Giancarlo and Wagner, Gerd and Guarino, Nicola and van Sinderen, Marten}, Booktitle = {Proc. Intl. Conf. on Advanced Information Systems Engineering (CAiSE)}, Citeseercitationcount = {0}, Conference-Abbr = {CAiSE}, Keywords = {UML Ontology Conceptual Modelling GOL}, Owner = {Tim Furche}, Pages = {112--126}, Publisher = {Springer-Verlag}, Series = {LNCS}, Title = {{An Ontologically Well-Founded Profile for UML Conceptual Models}}, Url = {http://is.tm.tue.nl/staff/gwagner/CAiSE2004.pdf}, Urldate = {2005/01/02}, Volume = {3084}, Year = {2004}, Abstract = {UML class diagrams can be used as a language for expressing a conceptual model of a domain. In a series of papers we have been using the General Ontological Language (GOL) and its underlying upper level ontology to evaluate the ontological correctness of a conceptual UML class model and to develop guidelines for how the constructs of the UML should be used in conceptual modeling. In this paper, we focus on the UML metaconcepts of classes and objects from an ontological point of view. We use a philosophically and psychologically well-founded theory of classifiers to propose a UML profile for Ontology Representation and Conceptual Modeling. Moreover, we propose a design pattern based on this profile to target a recurrent problem in role modeling discussed in the literature. Finally, we demonstrate the relevance of the tools proposed by applying them to solve recurrent problems in the practice of conceptual modeling.}} @inproceedings{Guo.Shao.ea_XRANKRankedKeyword_SIGMOD_2003, Author = {Guo, Lin and Shao, Feng and Botev, Chavdar and Shanmugasundaram, Jayavel}, Booktitle = SIGMOD, Conference-Abbr = {SIGMOD}, Keywords = {XML query languages IR information retrieval ranking}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/InformationRetrieval/Languages/Guo.Shao.ea_XRANKRankedKeyword_SIGMOD_2003.pdf}, Title = {{XRANK: Ranked Keyword Search over XML Documents}}, Url = {http://www.cs.cornell.edu/People/jai/papers/XRank.pdf}, Year = {2003}, Abstract = {We consider the problem of efficiently producing ranked results for keyword search queries over hyperlinked XML documents. Evaluating keyword search queries over hierarchical XML documents, as opposed to (conceptually) flat HTML documents, introduces many new challenges. First, XML keyword search queries do not always return entire documents, but can return deeply nested XML elements that contain the desired keywords. Second, the nested structure of XML implies that the notion of ranking is no longer at the granularity of a document, but at the granularity of an XML element. Finally, the notion of keyword proximity is more complex in the hierarchical XML data model. In this paper, we present the XRANK system that is designed to handle these novel features of XML keyword search. Our experimental results show that XRANK offers both space and performance benefits when compared with existing approaches. An interesting feature of XRANK is that it naturally generalizes a hyperlink based HTML search engine such as Google. XRANK can thus be used to query a mix of HTML and XML documents.}} @inproceedings{Guo.Li.ea_ScalableXSLTEvaluation_APWEB_2004, Author = {Guo, Zhimao and Li, Min and Wang, Xiaoling and Zhou, Aoying}, Booktitle = {Proc. Asia Pacific Web Conference}, Conference-Abbr = {APWEB}, Keywords = {XML XSLT evaluation optimization query languages}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/XSLT/Guo.Li.ea_ScalableXSLTEvaluation_APWEB_2004.pdf}, Title = {{Scalable XSLT Evaluation}}, Url = {http://arxiv.org/abs/cs.DB/0408051}, Year = {2004}, Abstract = {XSLT is an increasingly popular language for processing XML data. It is widely supported by application platform software. However, little optimization effort has been made inside the current XSLT processing engines. Evaluating a very simple XSLT program on a large XML document with a simple schema may result in extensive usage of memory. In this paper, we present a novel notion of \emph{Streaming Processing Model} (\emph{SPM}) to evaluate a subset of XSLT programs on XML documents, especially large ones. With SPM, an XSLT processor can transform an XML source document to other formats without extra memory buffers required. Therefore, our approach can not only tackle large source documents, but also produce large results. We demonstrate with a performance study the advantages of the SPM approach. Experimental results clearly confirm that SPM improves XSLT evaluation typically 2 to 10 times better than the existing approaches. Moreover, the SPM approach also features high scalability.}} @article{Hamilton.Selinger_ConversationwithPat_ACMQ_2005, Author = {Hamilton, James and Selinger, Pat}, Journal = {ACM Queue}, Journal-Abbr = {ACMQ}, Keywords = {database vision metadata unstructured information}, Number = {3}, Owner = {Tim Furche}, Title = {{A Conversation with Pat Selinger}}, Url = {http://www.acmqueue.org/modules.php?name=Content&pa=showpage&pid=297&page=1}, Volume = {3}, Year = {2005}, Abstract = {Take Pat Selinger of IBM and James Hamilton of Microsoft and put them in a conversation together, and you may hear everything you wanted to know about database technology and weren?t afraid to ask.}} @article{Henze.Dolog.ea_ReasoningandOntologies_ETS_2004, Author = {Henze, Nicola and Dolog, Peter and Nejdl, Wolfgang}, Journal = {Educational Technology Society}, Journal-Abbr = {ETS}, Keywords = {Personalization Personal Reader E-Learning Semantic Web}, Owner = {Tim Furche}, Pdf = {ApplicationAreas/Personalization/Henze.Dolog.ea_ReasoningandOntologies_ETS_2004.pdf}, Title = {{Reasoning and Ontologies for Personalized E-Learning}}, Url = {http://www.kbs.uni-hannover.de/Arbeiten/Publikationen/2004/ifets_final.pdf}, Year = {2004}, Abstract = {The challenge of the semantic web is the provision of distributed information with well defined meaning, understandable for different parties. Particularly, applications should be able to provide individually optimized access to information by taking the individual needs and requirements of the users into account. In this paper we propose a framework for personalized e-Learning in the semantic web and show how the semantic web resource description formats can be utilized for automatic generation of hypertext structures from distributed metadata. Ontologies and metadata for three types of resources (domain, user, and observation) are investigated. We investigate a logic-based approach to educational hypermedia using TRIPLE, a rule and query language for the semantic web.}} @inproceedings{Henze.Herrlich_PersonalReader-Framework_ABIS_2004, Author = {Henze, Nicola and Herrlich, Marc}, Booktitle = {Proc. Workshop on Adaptation and User Modeling in Interactive Systems}, Conference-Abbr = {ABIS}, Keywords = {Personalization Semantic Web Personal Reader RDF}, Owner = {Tim Furche}, Pdf = {ApplicationAreas/Personalization/Henze.Herrlich_PersonalReader-Framework_ABIS_2004.pdf}, Title = {{The Personal Reader: A Framework for Enabling Personalization Services on the Semantic Web}}, Url = {http://www.kbs.uni-hannover.de/Arbeiten/Publikationen/2004/Personal_Reader_abis04.pdf}, Year = {2004}, Abstract = {The Personal Reader provides a framework for designing, implementing and maintaining web content readers, which provide personalized enrichment of web content for each individual user. The idea of the the Personal Reader is based on a rigorous approach for applying Semantic Web technologies: A modular framework of components / services - for visualizing the Personal Reader and providing the user interface, for mediating between user requests and available personalization services, and for providing personalized recommendations and access to web content forms the basis for the Personal Reader. In this paper, we describe the architectural outline of the framework as well as some implementation details, and discuss the approach with a reference - a ?Personal Reader for Learning Resources?.}} @article{Henze.Nejdl_LogicalCharacterizationof_NRHM_2004, Author = {Henze, Nicola and Nejdl, Wolfgang}, Journal = {New Revies on Hypertext and Hypermedia}, Journal-Abbr = {NRHM}, Keywords = {Personalization Personal Reader Logic Semantic Web}, Owner = {Tim Furche}, Pdf = {ApplicationAreas/Personalization/Henze.Nejdl_LogicalCharacterizationof_NRHM_2004.pdf}, Title = {{A Logical Characterization of Adaptive Educational Hypermedia}}, Url = {http://www.kbs.uni-hannover.de/Arbeiten/Publikationen/2004/logical_characterization_henze_nejdl.pdf}, Year = {2004}, Abstract = {Currently, adaptive educational hypermedia systems (AEHS) are described with nonuniform methods, depending on the specific view on the system, the application, or other parameters. There is no common language for expressing functionality of AEHS, hence these systems are difficult to compare and analyze. In this paper we investigate how a logical description can be employed to characterize adaptive educational hypermedia. We propose a definition of AEHS based on first-order logic, characterize some AEHS due to this formalism, and discuss the applicability of this approach.}} @inproceedings{Hidders_SatisfiabilityofXPath_DBPL_2003, Author = {Hidders, Jan}, Booktitle = {Intl. Workshop on Databse Programming Languages}, Conference-Abbr = {DBPL}, Keywords = {XML XPath satisfiability query languages theory}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/PathExpressions/XPath/Hidders_SatisfiabilityofXPath_DBPL_2003.pdf}, Title = {{Satisfiability of XPath Expressions}}, Url = {http://plantijn.ruca.ua.ac.be/~adrem/biborb/bibs/ADReM/papers/hidders03xpathsat.pdf}, Year = {2003}, Abstract = {In this paper, we investigate the complexity of deciding the satisfiability of XPath 2.0 expressions, i.e., whether there is an XML document for which their result is nonempty. Several fragments that allow certain types of expressions are classified as either in PTIME or NP-hard to see which type of expression make this a hard problem. Finally, we establish a link between XPath expressions and partial tree descriptions which are studied in computational linguistics.}} @inproceedings{Horst_ExtendingRDFSEntailment_ISWC_2004, Author = {ter Horst, Herman J.}, Booktitle = ISWC # {, Hiroshima, Japan}, Comment = {Two essential contributions: the notion of ?partial closure? of an RDF graph G. In contrast to the closure graph of G defined in [Hayes, RDF-MT, W3C Recommendation, 2004] that is infinite (due to the infinite number of axiomatic triples for all rdf:_i properties), the partial closure is finite by considering only the axiomatic triples for all rdf:_i actually occuring in the G. The second contribution of this paper is an interesting restriction of OWL-DL (containing, e.g., owl:FunctionalProperty, owl:InverseFunctionalProperty, owl:sameAs, owl:inverseOf) together with an interpretation and a set of entailment rules. This could be a good start for an implementation of a restricted form of OWL on top of Xcerpt.}, Conference-Abbr = {ISWC}, Keywords = {RDF Entailment RDFS}, Owner = {Tim Furche}, Pdf = {SemanticWeb/RDF/RDFS/Horst_ExtendingRDFSEntailment_ISWC_2004.pdf}, Title = {{Extending the RDFS Entailment Lemma}}, Url = {http://xobjects.seu.edu.cn/resource/ISWC2004/abstracts/32980077.html}, Urldate = {2004/11/24}, Year = {2004}, Abstract = {We complement the RDF semantics specification of the W3C by proving decidability of RDFS entailment. Furthermore, we show completeness and decidability of entailment for RDFS extended with datatypes and a property-related fragment of OWL. The RDF semantics specification provides a complete set of entailment rules for reasoning with RDFS, but does not prove decidability of RDFS entailment: the closure graphs used in the completeness proof are infinite for finite RDF graphs. We define partial closure graphs, which can be taken to be finite for finite RDF graphs, which can be computed in polynomial time, and which are sufficient to decide RDFS entailment. We consider the extension of RDFS with datatypes and a property-related fragment of OWL: FunctionalProperty, InverseFunctionalProperty, sameAs, SymmetricProperty, TransitiveProperty, and inverseOf. In order to obtain a complete set of simple entailment rules, the semantics that we use for these extensions is in line with the 'if-semantics' of RDFS, and weaker than the 'iff-semantics' defining D-entailment and OWL (DL or Full) entailment. Classes can be used as instances, the use of FunctionalProperty and TransitiveProperty is not restricted to obtain decidability, and a partial closure that is sufficient for deciding entailment can be computed in polynomial time.}} @inproceedings{HungDeng.RDF-Aggregate-Querie.2005, Author = {Hung, E. and Deng, Y. and Subrahmanian, V. S.}, Booktitle = {Proc. Intl. Conf. on Data Engineering}, Conference-Abbr = {ICDE}, Date-Added = {2005-05-01 22:35:19 +0200}, Date-Modified = {2005-05-01 22:35:55 +0200}, Title = {{RDF Aggregate Queries and Views}}, Year = {2005}} @inproceedings{Jain.Mahajan.ea_TranslatingXSLTPrograms_WWW_2002, Author = {Jain, Sushant and Mahajan, Ratul and Suciu, Dan}, Booktitle = WWW, Conference-Abbr = {WWW}, Doi = {http://doi.acm.org/10.1145/511446.511526}, Isbn = {1-58113-449-5}, Keywords = {XML XSTL query processing relational implementation SQL}, Location = {Honolulu, Hawaii, USA}, Pages = {616--626}, Publisher = {ACM Press}, Title = {{Translating XSLT Programs to Efficient SQL Queries}}, Url = {http://www2002.org/CDROM/refereed/226/}, Year = {2002}, Abstract = {We present an algorithm for translating XSLT programs into SQL. Our context is that of virtual XML publishing, in which a single XML view is defined from a relational database, and subsequently queried with XSLT programs. Each XSLT program is translated into a single SQL query and run entirely in the database engine. Our translation works for a large fragment of XSLT, which we define, that includes descendant/ancestor axis, recursive templates, modes, parameters, and aggregates. We put considerable effort in generating correct and efficient SQL queries and describe several optimization techniques to achieve this efficiency. We have tested our system on all 22 SQL queries of the TPC-H database benchmark which we represented in XSLT and then translated back to SQL using our translator.}} @inproceedings{Johnson.Shneiderman_Tree-maps-Space-FillingApproach_Vis_1991, Author = {Johnson, Brian and Shneiderman, Ben}, Booktitle = {Proc. Intl. Conf.on Visualization}, Conference-Abbr = {Vis}, Keywords = {visualization hiearchical structures tree map}, Owner = {Tim Furche}, Pages = {284--291}, Pdf = {QueryEvaluation/XML/Visualization/Johnson.Shneiderman_Tree-maps-Space-FillingApproach_Vis_1991.pdf}, Title = {{Tree-maps: a Space-Filling Approach to the Visualization of Hierarchical Information Structures}}, Url = {http://ieeexplore.ieee.org/search/srchabstract.jsp?arnumber=175815&isnumber=4467&punumber=362&k2dockey=175815@ieeecnfs&query=%28shneiderman+b.%3CIN%3Eau+%29&pos=1&arSt=284&ared=291&arAuthor=Johnson%2C+B.%3B+Shneiderman%2C+B.%3B}, Year = {1991}, Abstract = {A method for visualizing hierarchically structured information is described. The tree-map visualization technique makes 100% use of the available display space, mapping the full hierarchy onto a rectangular region in a space-filling manner. This efficient use of space allows very large hierarchies to be displayed in their entirety and facilitates the presentation of semantic information. Tree-maps can depict both the structure and content of the hierarchy. However, the approach is best suited to hierarchies in which the content of the leaf nodes and the structure of the hierarchy are of primary importance, and the content information associated with internal nodes is largely derived from their children}} @book{Katz.Chamberlin.ea_XQueryfromExperts_2003, Author = {Katz, Howard and Chamberlin, Don and Draper, Denise and Fernandez, Mary and Kay, Michael and Robie, Jonathan and Rys, Michael and Simeon, Jerome and Tivy, Jim and Wadler., Philip}, Edition = {1st}, Owner = {Tim Furche}, Publisher = {Addison-Wesley}, Title = {{XQuery from the Experts: A Guide to the W3C XML Query Language}}, Year = {2003}} @book{Kay_XPath-2.0Programmer-sReference_2004, Author = {Kay, Michael}, Keywords = {XML XPath query query languages}, Owner = {Tim Furche}, Publisher = {John Wiley}, Title = {{XPath 2.0 Programmer's Reference}}, Year = {2004}, Abstract = {XPath 2.0 Programmer's Reference is the only authoritative reference on XPath, a sub-language within XSLT that determines which part of an XML document the XSLT transforms. Written for professional programmers who use XML every day but find the W3C XPath specifications tough to slog through, this book explains in everyday language what every construct in the language does and how to use it. It also offers background material on the design thinking behind the language, gentle criticism of the language specification when appropriate, and a diverse range of interesting examples in various application areas.}} @book{Kay_XSLT2.0Programmers_2004, Author = {Kay, Michael}, Edition = {3rd}, Keywords = {XML XSLT Programming Query languages}, Owner = {Tim Furche}, Publisher = {John Wiley}, Title = {{XSLT 2.0 Programmer's Reference}}, Year = {2004}, Abstract = {XSLT 2.0 Programmer's Reference, 3rd Edition, is the authoritative reference guide to the language. Without using the formal and inaccessible language of the W3C specifications, it tells you exactly what every construct in the language does, and how it is intended to be used. This book is a reference rather than a tutorial; it is designed for the professional programmer who is using the language every day. It is the book that people quote when they claim that a particular product is giving the wrong answer, and the book that implementers of the language turn to when they want clarification of the specifications. At the same time, the book is readable. Reviews of the previous editions of the XSLT Programmer?s Reference, which this book grew from, show that readers appreciate the background material on the design thinking behind the language, the essay on functional programming, the occasional dry wit, the gentle criticism of the language specification when appropriate, and the fact that the examples stray into a diverse range of interesting application areas.}} @inproceedings{Kay_XSLTandXPath_XMLE_2004, Author = {Kay, Michael}, Booktitle = {XML Europe}, Conference-Abbr = {XMLE}, Keywords = {XML XSLT XPath optimization saxon practical experiences}, Owner = {Tim Furche}, Title = {{XSLT and XPath Optimization}}, Url = {http://idealliance.org/papers/dx_xmle04/papers/02-03-02/02-03-02.html}, Year = {2004}} @techreport{Kay.Walsh.ea_XSLT2.0and_TR_2005, Author = {Kay, Michael and Walsh, Norman and Zongaro, Henry and Boag, Scott and Tong, Joanne}, Institution = {W3C}, Keywords = {XML XQuery XSLT serialization query languages}, Owner = {Tim Furche}, Title = {{XSLT 2.0 and XQuery 1.0 Serialization}}, Type = {Working Draft}, Url = {http://www.w3.org/TR/xslt-xquery-serialization/This document defines serialization of an instance of the data model as defined in [Data Model] into a sequence of octets. [Definition: Serialization is designed to be a component of a expanded a host language such as[XSLT 2.0] or [XQuery 1.0].]}, Year = {2005}, Abstract = {This document defines serialization of an instance of the data model as defined in [Data Model] into a sequence of octets. [Definition: Serialization is designed to be a component of a expanded a host language such as[XSLT 2.0] or [XQuery 1.0].]}} @techreport{KlyneCarroll.Resource-Description.2004, Author = {Klyne, Graham and Carroll, Jeremy J. and McBride, Brian}, Date-Added = {2005-05-01 22:06:41 +0200}, Date-Modified = {2005-05-01 22:08:12 +0200}, Institution = {W3C}, Keywords = {RDF Semantic Web Concepts Abstract Syntax Primer}, Title = {{Resource Description Framework (RDF): Concepts and Abstract Syntax}}, Type = {Recommendation}, Url = {http://www.w3.org/TR/rdf-concepts/}, Year = {2004}, Abstract = {The Resource Description Framework (RDF) is a framework for representing information in the Web. RDF Concepts and Abstract Syntax defines an abstract syntax on which RDF is based, and which serves to link its concrete syntax to its formal semantics. It also includes discussion of design goals, key concepts, datatyping, character normalization and handling of URI references.}} @inproceedings{Koch.Scherzinger.ea_FluXQuery-OptimizingXQuery_VLDB_2004, Author = {Koch, Christoph and Scherzinger, Stefanie and Schweikardt, Nicole and Stegmaier, Bernhard}, Bibsource = {DBLP, http://dblp.uni-trier.de}, Booktitle = VLDB, Conference-Abbr = {VLDB}, Ee = {http://www.vldb.org/conf/2004/RS6P2.PDF}, Keywords = {XML XQuery stream implementation FluXQuery}, Pdf = {QueryEvaluation/XML/XQuery/Koch.Scherzinger.ea_FluXQuery-OptimizingXQuery_VLDB_2004.pdf}, Title = {{FluXQuery: An Optimizing XQuery Processor for Streaming XML Data}}, Url = {http://www.wit.at/people/scherzinger/documents/demo.pdf}, Year = {2004}} @inproceedings{Koffina.Serfiotis.ea_IntegratingXMLData_DOPS_2005, Author = {Koffina, Ioanna and Serfiotis, Giorgos and Christophides, Vassilis and Tannen, Val and Deutsch, Alin}, Booktitle = {Dagstuhl Seminar on Semantic Interoperability and Integration}, Conference-Abbr = {DROPS}, Keywords = {integration , xml , rdf schema}, Number = {04391}, Pdf = {SemanticWeb/RDF/RDF-XML-Integration/Koffina.Serfiotis.ea_IntegratingXMLData_DOPS_2005.pdf}, Publisher = {IBFI}, Series = {Dagstuhl Seminar Proceedings}, Title = {{Integrating XML Data Sources using RDF/S Schemas: The ICS-FORTH Semantic Web Integration Middleware (SWIM)}}, Url = {http://drops.dagstuhl.de/opus/volltexte/2005/34/pdf/04391.ChristophidesVassilis.Paper.34.pdf}, Year = {2005}, Abstract = {Semantic Web (SW) technology aims to facilitate the integration of legacy data sources spread worldwide. Despite the plethora of SW languages e.g., RDF/S, OWL recently proposed for supporting large scale information interoperation, the vast majority of legacy sources still rely on relational databases RDB published on the Web or corporate intranets as virtual XML. In this paper, we advocate a Datalog framework for mediating high level queries to relational and or XML sources using community ontologies expressed in a SW language such as RDF/S. We describe the architecture and the reasoning services of our SW integration middleware, called SWIM, and we present the main design choices and techniques for supporting powerful mappings between different data models, as well as reformulation and optimization of queries expressed against mediation schemas and views.}} @mastersthesis{Kraus_UseCasesfur_2004, Author = {Kraus, Sebastian}, Keywords = {XML Xcerpt use cases}, Pdf = {QueryEvaluation/Xcerpt/Kraus_UseCasesfur_2004.pdf}, School = {University of Munich}, Title = {{Use Cases f{\"u}r Xcerpt: Eine positionelle Anfrage- und Transformationssprache f{\"u}r das Web}}, Type = {{Diplomarbeit/Master thesis}}, Url = {http://www.pms.ifi.lmu.de/publikationen/#DA_Sebastian.Kraus}, Year = {2004}, Abstract = {In dieser Arbeit werden Anwendungsflle f{\"u}r die logische Anfragesprache Xcerpt vorgestellt und implementiert. Zweck dieser Arbeit ist hierbei, die Sprache Xcerpt, welche sich noch in einem Entwicklungszustand befindet, bez{\"u}glich ihrer Ausdrucksfhigkeit und Mchtigkeit zu untersuchen und gegebenenfalls notwendige und noch fehlende Konstrukte und Funktionalitten zu identifizieren. Hierbei werden zum einem die W3C Anwendungsflle f{\"u}r XQuery in Xcerpt implementiert, da diese wegen ihrer Vielzahl von unterschiedlichen Szenarien und somit unterschiedlichen Anfragen als Ma{\ss}stab f{\"u}r eine Anfragesprache herangezogen werden k{\"o}nnen. Zum anderen werden drei kleiner Anwendungsszenarien vorgestellt, die spezielle Fhigkeiten von Xcerpt hervorheben sollen. In dem ersten dieser Szenarien wird der internen Referenzmechanismus von Xcerpt vorgestellt. Da Xcerpt als Webanfragsprache konzipiert wurde, wird in der zweiten Anwendung ein Webcrawler vorgestellt. Die dritte Anwendung beinhaltet Xcerpt-Regel, wie sie ein Mediatorsystem verwenden k{\"o}nnte, um die Transformationsm{\"o}glichkeiten der Sprache hervorzuheben.}} @inproceedings{Li.Bohannon.ea_ComposingXSLTransformations_SIGMOD_2003, Author = {Li, Chengkai and Bohannon, Philip and Narayan, P. P. S.}, Booktitle = SIGMOD, Conference-Abbr = {SIGMOD}, Doi = {http://doi.acm.org/10.1145/872757.872820}, Isbn = {1-58113-634-X}, Keywords = {XML XSLT view query rewriting evaluation optimization}, Location = {San Diego, California}, Pages = {515--526}, Publisher = {ACM Press}, Title = {{Composing XSL Transformations with XML Publishing Views}}, Url = {http://www.ews.uiuc.edu/~cli/417-li.pdf}, Year = {2003}, Abstract = {While the XML Stylesheet Language for Transformations (XSLT) was not designed as a query language, it is well-suited for many query-like operations on XML documents including selecting and restructuring data. Further, it actively fulfills the role of an XML query language in modern applications and is widely supported by application platform software. However, the use of database techniques to optimize and execute XSLT has only recently received attention in the research community. In this paper, we focus on the case where XSL transformations are to be run on XML documents defined as views of relational databases. For a subset of XSLT, we present an algorithm to compose a transformation with an XML view, eliminating the need for the XSLT execution. We then describe how to extend this algorithm to handle several additional features of XSLT, including a proposed approach for handling recursion.}} @inproceedings{Liu.Vincent_Querytranslationfrom_DEAS_2003, Author = {Liu, Jixue and Vincent, Millist}, Booktitle = {Proc. Intl. Database Engineering and Applications Symposium}, Conference-Abbr = {DEAS}, Keywords = {XML XSLT relational implementation SQL query evaluation}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/XSLT/Liu.Vincent_Querytranslationfrom_DEAS_2003.pdf}, Title = {{Query translation from XSLT to SQL}}, Year = {2003}, Abstract = {XML has been accepted as a universal format for data interchange and publication. It can be applied in the applications in which the data of a database needs to be viewed in XML format so that the data being viewed takes more semantics and is easily understood. In these applications, the user of the data to be viewed sees only XML data, not the database. He may use XML query languages such as XSLT to query data and the retrieved data is presented in XML format to them. We are interested in the connection between the data that the user sees and the data in the database. More specifically, we are interested in translating XSLT queries to SQL queries.}} @techreport{Malhotra.Melton.ea_XQuery1.0and_TR_2005, Author = {Malhotra, Ashok and Melton, Jim and Walsh, Norman}, Institution = {W3C}, Keywords = {XML XQuery Functuions Operators XPath W3C Query Query Languages}, Owner = {Tim Furche}, Title = {{XQuery 1.0 and XPath 2.0 Functions and Operators}}, Type = {Working Draft}, Url = {http://www.w3.org/TR/xpath-functions/}, Urldate = {2005/01/31}, Year = {2005}, Abstract = {This document defines basic operators and functions on the datatypes defined in [XML Schema Part 2: Datatypes Second Edition] and the datatypes defined in [XQuery 1.0 and XPath 2.0 Data Model] and in this document for use in [XPath 2.0], [XQuery 1.0: An XML Query Language] and [XSLT 2.0] and other related XML standards. It also discusses operators and functions on nodes and node sequences as defined in the [XQuery 1.0 and XPath 2.0 Data Model] for use in [XPath 2.0], [XQuery 1.0: An XML Query Language] and [XSLT 2.0] and other related XML standards.}} @techreport{Manola.Miller.ea_RDFPrimer_TR_2004, Author = {Manola, Frank and Miller, Eric and McBride, Brian}, Date-Added = {2005-05-01 22:06:41 +0200}, Date-Modified = {2005-05-01 22:08:12 +0200}, Institution = {W3C}, Keywords = {RDF Semantic Web Concepts Abstract Syntax}, Title = {{RDF Primer}}, Type = {Recommendation}, Url = {http://www.w3.org/TR/rdf-primer/}, Year = {2004}, Abstract = {The Resource Description Framework (RDF) is a language for representing information about resources in the World Wide Web. This Primer is designed to provide the reader with the basic knowledge required to effectively use RDF. It introduces the basic concepts of RDF and describes its XML syntax. It describes how to define RDF vocabularies using the RDF Vocabulary Description Language, and gives an overview of some deployed RDF applications. It also describes the content and purpose of other RDF specification documents.}} @inproceedings{Manola.Pirotte_CQLF---aQueryLanguage_SIGMOD_1982, Author = {Manola, Frank and Pirotte, Alain}, Booktitle = SIGMOD, Conference-Abbr = {SIGMOD}, Doi = {http://doi.acm.org/10.1145/582353.582369}, Isbn = {0-89791-073-7}, Keywords = {CODASYL network databases query languages CQLF path expressions}, Location = {Orlando, Florida}, Pages = {94--103}, Pdf = {QueryEvaluation/Languages/Manola.Pirotte_CQLF---aQueryLanguage_SIGMOD_1982.pdf}, Publisher = {ACM Press}, Title = {{CQLF---a Query Language for CODASYL-type Databases}}, Url = {http://portal.acm.org/citation.cfm?id=582369}, Year = {1982}, Abstract = {This paper describes CQLF (CODASYL Query Language, Flat) [MAN081]. CQLF is a high level language for accessing and manipulating data in databases described using the 1981 ANSI dpANS version of the CODASYL Data Description Language [ANSI81]. CQLF has similarities to typical relational languages, such as SQL [ASTR76, CHAM76] and QUEL [STON76]. CQLF provides capabilities for querying and operating on databases described both in a "relational style" (having no CODASYL sets, using only values to represent interrecord relationships, and having records with no arrays), and in a "network style" (using CODASYL sets to represent interrecord relationships, and having records containing arrays).}} @inproceedings{Martens.Neven_FrontiersofTractability_PODS_2004, Author = {Martens, Wim and Neven, Frank}, Booktitle = PODS, Conference-Abbr = {PODS}, Keywords = {XML transformations type checking tractability}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/XSLT/Martens.Neven_FrontiersofTractability_PODS_2004.pdf}, Title = {{Frontiers of Tractability for Typechecking Simple XML Transformations}}, Url = {http://www.sigmod.org/sigmod/pods/proc04/pdf/P-03.pdf}, Year = {2004}} @inproceedings{May.Helmer.ea_QuantifiersinXQuery_WISE_2003, Author = {May, Norman and Helmer, Sven and Moerkotte, Guido}, Booktitle = {Proc. Intl. Conf. on Web Information Systems Engineering}, Conference-Abbr = {WISE}, Keywords = {XML XQuery quantifiers nested queries optimization rewriting}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/XQuery/May.Helmer.ea_QuantifiersinXQuery_WISE_2003.pdf}, Title = {{Quantifiers in XQuery}}, Url = {http://pi3.informatik.uni-mannheim.de/~norman/unnesting_wise03.pdf}, Year = {2003}, Abstract = {We present algebraic equivalences that allow to unnest nested algebraic expressions containing quantifiers for order-preserving algebraic operators. We illustrate how these equivalences can be applied successfully to unnest nested queries formulated in XQuery. Measurements illustrate the performance gains possible by unnesting.}} @inproceedings{Meuss.Schulz.ea_TowardsAggregatedAnswers_ICDT_2001, Author = {Meuss, Holger and Schulz, Klaus U. and Bry, Fran{\c c}ois}, Booktitle = {Proc. Intl. Conf. on Database Theory}, Conference-Abbr = {ICDT}, Isbn = {3-540-41456-8}, Keywords = {XML query languages CAA navigation theory path visualization}, Pages = {346--360}, Publisher = {Springer-Verlag}, Title = {{Towards Aggregated Answers for Semistructured Data}}, Url = {http://www.pms.ifi.lmu.de/publikationen#PMS-FB-2000-15}, Year = {2001}, Abstract = {Semistructured data are usually formalized as trees or more generally as graphs. Query languages for semistructured data have been proposed that, like SQL, can be seen as involving a number of variables, but, in contrast to SQL, arrange the variables in trees or graphs reflecting the structure of the semistructured data to be retrieved. Leaving aside the ``construct'' parts of queries, answers can be formalized as mappings represented as tuples, hence called answer tuples, that assign database nodes to query variables. These answer tuples underly the semistructured data delivered as answers. A simple enumeration of answer tuples following the old relational approach is problematic for several reasons. First, the number of answer tuples for a query may grow exponentially in the size of both, the query and the database. Second, even if the number of answer tuples is manageable, the frequent sharing of common data between distinct answer tuples is no more apparent in their enumeration. In this article, it is first argued that, in the context of semistructured data, enumerating answer tuples is often inappropriate and that aggregated answers are preferable. Then, a notion of aggregated answers called complete answer aggregate (CAA) is introduced and algorithms for computing CAAs are given. It is shown that CAAs enjoy nice complexity properties: (1) While the number of answer tuples may be exponential in the size of the query, the size of the CAA is at most linear in the size of the query and quadratic in the size of the database; (2) the complexity of computing the CAA of a query depends on the query's structural complexity (i.e. whether it is a sequence, tree, graph, etc.) but is independent of the structural complexity of the database. For tree queries, efficient polynomial algorithms are given. Besides, it is argued that CAAs are particularly appropriate for answer searching and answer browsing.}} @article{Meuss.Schulz.ea_VisualExplorationand_JDL_2005, Author = {Meuss, Holger and Schulz, Klaus U. and Weigel, Felix and Leonardi, Simone and Bry, Fran{\c c}ois}, Journal = {Journal on Digital Libraries}, Journal-Abbr = {JDL}, Keywords = {XML query languages visualization exploration X2 CAA}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/Visualization/Meuss.Schulz.ea_VisualExplorationand_JDL_2005.pdf}, Title = {{Visual Exploration and Retrieval of XML Document Collections with the Generic System X2}}, Url = {http://www.cis.uni-muenchen.de/~weigel/Literatur/meuss04visual.pdf}, Year = {2005}, Abstract = {This article reports on the XML retrieval system X2 which has been developed at the University of Munich over the last five years. In a typical session with X2, the user first browses a structural summary of the XML database in order to select interesting elements and keywords occurring in documents. Using this intermediate result, queries combining structure and textual references are composed semiautomatically. After query evaluation, the full set of answers is presented in a visual and structured way. X2 largely exploits the structure found in documents, queries and answers to enable new interactive visualization and exploration techniques that support mixed IR and database-oriented querying, thus bridging the gap between these three views on the data to be retrieved. Another salient characteristic of X2 which distinguishes it from other visual query systems for XML is that it supports various degrees of detailedness in the presentation of answers, as well as techniques for dynamically reordering and grouping retrieved elements once the complete answer set has been computed.}} @inproceedings{Meyer.Bruder.ea_XircusSearchEngine_INEX_2002, Author = {Meyer, Holger and Bruder, Ilvio and Heuer, Andreas and Weber, Gunnar}, Bibsource = {DBLP, http://dblp.uni-trier.de}, Booktitle = {INEX Workshop}, Conference-Abbr = {INEX}, Pages = {119-124}, Title = {{The Xircus Search Engine}}, Year = {2002}, Abstract = {Nowadays, XML is the document model in favour for both document- and data-centric web applications. Its influence in other, more traditional projects and applications grows as the web and associated techniques become the de-facto standard in user interfaces in such systems. We present an XML-sensitive search engine (Xircus) suited for processing semi-structured queries over large collections of XML documents. Xircus is based on state of the art information retrieval techniques. It is a test bed for research in query processing for XML and semistructured data in general.}} @inproceedings{Miklau.Suciu_ContainmentandEquivalence_PODS_2002, Author = {Miklau, Gerome and Suciu, Dan}, Booktitle = PODS, Conference-Abbr = {PODS}, Doi = {http://doi.acm.org/10.1145/543613.543623}, Isbn = {1-58113-507-6}, Keywords = {XML XPath fragment containment query languages}, Location = {Madison, Wisconsin}, Pages = {65--76}, Pdf = {QueryEvaluation/PathExpressions/XPath/Miklau.Suciu_ContainmentandEquivalence_PODS_2002.pdf}, Publisher = {ACM Press}, Title = {{Containment and Equivalence for an XPath Fragment}}, Url = {http://www.cs.washington.edu/homes/suciu/pods2002MS.pdf}, Year = {2002}, Abstract = {XPath is a simple language for navigating an XML document and selecting a set of element nodes. XPath expressions are used to query XML data, describe key constraints, express transformations, and reference elements in remote documents. This paper studies the containment and equivalence problems for a fragment of the XPath query language, with applications in all these contexts.In particular, we study a class of XPath queries that contain branching, label wildcards and can express descendant relationships between nodes. Prior work has shown that languages which combine any two of these three features have efficient containment algorithms. However, we show that for the combination of features, containment is coNP-complete. We provide a sound and complete EXPTIME algorithm for containment, and study parameterized PTIME special cases. While we identify two parameterized classes of queries for which containment can be decided efficiently, we also show that even with some bounded parameters, containment is coNP-complete. In response to these negative results, we describe a sound algorithm which is efficient for all queries, but may return false negatives in some cases.}} @inproceedings{Munroe.Papakonstantinou_BBQ-VisualInterface_VDB_2000, Author = {Munroe, Kevin D. and Papakonstantinou, Yannis}, Booktitle = {Proc. Conf. on Visual Database Systems}, Conference-Abbr = {VDB}, Isbn = {0-7923-7835-0}, Keywords = {XML query visualization XMAS BBQ interface}, Pages = {277--296}, Pdf = {QueryEvaluation/XML/Visualization/Munroe.Papakonstantinou_BBQ-VisualInterface_VDB_2000.pdf}, Publisher = {Kluwer, B.V.}, Title = {{BBQ: A Visual Interface for Integrated Browsing and Querying of XML}}, Url = {http://www.db.ucsd.edu/publications/bbq.pdf}, Year = {2000}, Abstract = {In this paper we present BBQ (Blended Browsing and Querying), a graphic user interface for seamlessly browsing and querying XML data sources. BBQ displays the structure of multiple data sources using a paradigm that resembles drilling-down in Windows? directory structures. BBQ allows queries incorporating one or more of the sources. Queries are constructed in a query-by-example (QBE) manner, where DTDs play the role of schema. The queries are arbitrary conjunctive queries with GROUPBY, and their results can be subsequently used and refined. To support query refinement, BBQ introduces virtual result views: standalone virtual data sources that (i) are constructed by user queries, from elements in other data sources, and (ii) can be used in subsequent queries as first-class data sources themselves. Furthermore, BBQ allows users to query data sources with loose or incomplete schema, and can augment such schema with a DTD inference mechanism.}} @inproceedings{Murata.Tozawa.ea_XMLAccessControl_CCS_2003, Author = {Murata, Makoto and Tozawa, Akihiko and Kudo, Michiharu and Hada, Satoshi}, Booktitle = {Proc. ACM Conf. on Computer and Communications Security}, Conference-Abbr = {CCS}, Doi = {http://doi.acm.org/10.1145/948109.948122}, Isbn = {1-58113-738-9}, Keywords = {XML XQuery access control policy}, Location = {Washington D.C., USA}, Pages = {73--84}, Pdf = {QueryEvaluation/XML/XQuery/Murata.Tozawa.ea_XMLAccessControl_CCS_2003.pdf}, Publisher = {ACM Press}, Title = {{XML Access Control using Static Analysis}}, Url = {http://portal.acm.org/citation.cfm?id=948122}, Year = {2003}, Abstract = {Access control policies for XML typically use regular path expressions such as XPath for specifying the objects for access control policies. However such access control policies are burdens to the engines for XML query languages. To relieve this burden, we introduce static analysis for XML access control. Given an access control policy, query expression, and an optional schema, static analysis determines if this query expression is guaranteed not to access elements or attributes that are permitted by the schema but hidden by the access control policy. Static analysis can be performed without evaluating any query expression against an actual database. Run-time checking is required only when static analysis is unable to determine whether to grant or deny access requests. A nice side-effect of static analysis is query optimization: access-denied expressions in queries can be evaluated to empty lists at compile time. We have built a prototype of static analysis for XQuery, and shown the effectiveness and scalability through experiments.}} @inproceedings{ONeil.ONeil.ea_ORDPATHs-Insert-friendlyXML_SIGMOD_2004, Author = {O'Neil, Patrick and O'Neil, Elizabeth and Pal, Shankar and Cseri, Istvan and Schaller, Gideon and Westbury, Nigel}, Booktitle = SIGMOD, Conference-Abbr = {SIGMOD}, Doi = {http://doi.acm.org/10.1145/1007568.1007686}, Isbn = {1-58113-859-8}, Keywords = {XML encoding XQuery relational implementation}, Location = {Paris, France}, Pages = {903--908}, Pdf = {QueryEvaluation/XML/XQuery/O'Neil.O'Neil.ea_ORDPATHs-Insert-friendlyXML_SIGMOD_2004.pdf}, Publisher = {ACM Press}, Title = {{ORDPATHs: Insert-friendly XML Node Labels}}, Url = {http://www.cs.umb.edu/~poneil/ordpath.pdf}, Year = {2004}, Abstract = {We introduce a hierarchical labeling scheme called ORDPATH that is implemented in the upcoming version of Microsoft{\textregistered} SQL Server?. ORDPATH labels nodes of an XML tree without requiring a schema (the most general case---a schema simplifies the problem). An example of an ORDPATH value display format is "1.5.3.9.1". A compressed binary representation of ORDPATH provides document order by simple byte-by-byte comparison and ancestry relationship equally simply. In addition, the ORDPATH scheme supports insertion of new nodes at arbitrary positions in the XML tree, their ORDPATH values "careted in" between ORDPATHs of sibling nodes, without relabeling any old nodes.}} @article{Oliboni.Tanca_VisualLanguageshould_IS_2002, Author = {Oliboni, Barbara and Tanca, Letizia}, Doi = {http://dx.doi.org/10.1016/S0306-4379(02)00007-8}, Issn = {0306-4379}, Journal = {Information Systems}, Journal-Abbr = {IS}, Keywords = {XML query languages XML-GL recursion}, Number = {7}, Pages = {459--486}, Publisher = {Elsevier Science Ltd.}, Title = {{A Visual Language should be easy to use: a Step Forward for XML-GL}}, Volume = {27}, Year = {2002}, Abstract = {XML is spreading out as a standard for semistructured documents on the Web, so the possibility of querying XML documents which are linked by XML links is becoming a goal to achieve. In this paper we present XML-GLrec, an extended version of the graphical query language for XML documents XML-GL. XML-GL allows to extract and restructure information from XML specified WWW documents. We extend XML-GL in the following directions: (i) XML-GLrec allows to represent XML simple finks, so that it is possible to query whole XML specified WWW sites in a simple and intuitive way; (ii) XML-GLrec improves the expressive power of XML-GL, where only transitive closure can be expressed, by allowing generic recursion; (iii) finally, we permit the user to specify queries in an easier fashion, by allowing sequences of nested query, in the same way as in SQL.}} @phdthesis{Olteanu_EvaluationofXPath_2005, Author = {Olteanu, Dan}, Keywords = {XML query streams rewriting forward XPath LGQ complexity query languages XPath SPEX}, Owner = {Tim Furche}, School = {University of Munich}, Title = {{Evaluation of XPath Queries against XML Streams}}, Type = {{Dissertation/Ph.D. thesis}}, Year = {2005}, Abstract = {XML is nowadays the de facto standard for electronic data interchange on the Web. Available XML data ranges from small Web pages to ever-growing repositories of, e.g., biological and astronomical data, and even to rapidly changing and possibly unbounded streams, as used in Web data integration and publish-subscribe systems. Animated by the ubiquity of XML data, the basic task of XML querying is becoming of great theoretical and practical importance. The last years witnessed efforts as well from practitioners, as also from theoreticians towards defining an appropriate XML query language. At the core of this common effort has been identified a navigational approach for information localization in XML data, comprised in a practical and simple query language called XPath [1]. This work brings together the two aforementioned ?worlds?, i.e., the XPath query evaluation and the XML data streams, and shows as well theoretical as also practical relevance of this fusion. Its relevance can not be subsumed by traditional database management systems, because the latter are not designed for rapid and continuous loading of individual data items, and do not directly support the continuous queries that are typical for stream applications. The first central contribution of this work consists in the definition and the theoretical investigation of three term rewriting systems to rewrite queries with reverse predicates, like parent or ancestor, into equivalent forward queries, i.e., queries without reverse predicates. Our rewriting approach is vital to the evaluation of queries with reverse predicates against unbounded XML streams, because neither the storage of past fragments of the stream, nor several stream traversals, as required by the evaluation of reverse predicates, are affordable. Beyond their declared main purpose of providing equivalences between queries with reverse predicates and forward queries, the applications of our rewriting systems shed light on other query language properties, like the expressivity of some of its fragments, the query minimization, or even the complexity of query evaluation. For example, using these systems, one can rewrite any graph query into an equivalent forward forest query. The second main contribution consists in a streamed and progressive evaluation strategy of forward queries against XML streams. The evaluation is specified using compositions of so-called stream processing functions, and is implemented using networks of deterministic pushdown transducers. The complexity of this evaluation strategy is polynomial in both the query and the data sizes for forward forest queries and even for a large fragment of graph queries. The third central contribution consists in two real monitoring applications that use directly the results of this work: the monitoring of processes running on UNIX computers, and a system for providing graphically real-time traffic and travel information, as broadcasted within ubiquitous radio signals.}} @inproceedings{Olteanu.Furche.ea_EfficientSingle-PassQuery_SAC_2004, Author = {Olteanu, Dan and Furche, Tim and Bry, Fran{\c c}ois}, Booktitle = {Data Streams Track,} # SAC, Conference-Abbr = {SAC}, Keywords = {REWERSE Query Languages Query Evaluation Streams SPEX XPath}, Organization = {ACM}, Pdf = {QueryEvaluation/Streams/XPath/Olteanu.Furche.ea_EfficientSingle-PassQuery_SAC_2004.pdf}, Title = {{An Efficient Single-Pass Query Evaluator for XML Data Streams}}, Url = {http://www.pms.ifi.lmu.de/publikationen/#PMS-FB-2004-1}, Urldate = {2004/11/11}, Year = {2004}, Abstract = {Data streams might be preferable to data stored in memory in contexts where the data is too large or volatile, or a standard approach to data processing based on data parsing and/or storing is too time or space consuming. Emerging applications such as publish-subscribe systems, data monitoring in sensor networks, financial and traffic monitoring, and routing of MPEG-7 call for querying data streams. In many such applications, XML streams are arguably more appropriate than flat data streams, for XML data is record-like, though not precluding multiple occurrences of fields with the same name. Evaluating selection queries against XML streams is especially challenging because XML data is structured (like records) and might have unbounded size.This paper proposes an efficient single-pass evaluator of XPath queries against XML data streams unbounded (possibly infinite) in size. The evaluator is based on networks of independent deterministic pushdown transducers and it is especially suitable for implementation on devices with low-memory and simple logic as used, e.g., in mobile computing.}} @inproceedings{Olteanu.Furche.ea_EvaluatingComplexQueries_BNCOD_2003, Author = {Olteanu, Dan and Furche, Tim and Bry, Fran{\c c}ois}, Booktitle = BNCOD, Conference-Abbr = {BNCOD}, Keywords = {Streams Path Expressions XML XPath Query Evaluation}, Pdf = {QueryEvaluation/Streams/XPath/Olteanu.Furche.ea_EvaluatingComplexQueries_BNCOD_2003.pdf}, Title = {{Evaluating Complex Queries against XML streams with Polynomial Combined Complexity}}, Url = {http://www.pms.ifi.lmu.de/publikationen/#PMS-FB-2003-15}, Urldate = {2004/11/11}, Year = {2003}, Abstract = {Querying of XML streams is receiving much attention due to its growing range of applications from traffic monitoring to routing of media streams. Existing approaches to querying XML streams consider restricted query language fragments, in most cases with exponential worst-case complexity in the size of the query. This paper investigates the complexity of the SPEX evaluation method. The combined complexity of this method is shown to be polynomial in the size of the data and the query. Extensive experimental evaluation with a prototype confirm the theoretical complexity results.}} @talk{Olteanu.Meuss.ea_SymmetryinXPath_SLIDES_2001, Author = {Olteanu, Dan and Meuss, Holger and Furche, Tim}, Institution = {Institute for Computer Science, University of Munich, Germany}, Keywords = {Path Expressions Query Evaluation Streams XML Presentation}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/PathExpressions/XPath/Olteanu.Meuss.ea_SymmetryinXPath_SLIDES_2001.pdf}, Title = {{Symmetry in XPath}}, Type = {Oberseminar ?Knowledge Representation and Markup Languages?}, Year = {2001}} @inproceedings{Olteanu.Meuss.ea_XPath-LookingForward_XMLDM_2002, Author = {Olteanu, Dan and Meuss, Holger and Furche, Tim and Bry, Fran{\c c}ois}, Booktitle = {Proc. EDBT Workshop on XML-Based Data Management}, Conference-Abbr = {XMLDM}, Pdf = {QueryEvaluation/PathExpressions/XPath/Olteanu.Meuss.ea_XPath-LookingForward_XMLDM_2002.pdf}, Publisher = {Springer-Verlag}, Series = {LNCS}, Title = {{XPath: Looking Forward}}, Url = {http://www.pms.ifi.lmu.de/publikationen/#PMS-FB-2002-4}, Urldate = {2004/11/11}, Volume = {2490}, Year = {2002}, Abstract = {The location path language XPath is of particular importance for XML applications since it is a core component of many XML processing standards such as XSLT or XQuery. In this paper, based on axis symmetry of XPath, equivalences of XPath 1.0 location paths involving ?reverse axes?, such as ancestor and preceding, are established. These equivalences are used as rewriting rules in an algorithm for transforming location paths with reverse axes into equivalent reverse-axis-free ones. Location paths without reverse axes as generated by the presented rewriting algorithm enable efficient SAX-like streamed data processing of XPath.}} @inproceedings{Olteanu.Meuss.ea_SymmetryinXPath_RMT_2001, Author = {Olteanu, Dan and Meuss, Holger and Furche, Tim and Bry, Fran{\c c}ois}, Booktitle = {Proc. Seminar on Rule Markup Techniques, Schloss Dagstuhl}, Conference-Abbr = {RMT}, Pdf = {QueryEvaluation/Streams/XPath/Olteanu.Meuss.ea_SymmetryinXPath_RMT_2001.pdf}, Title = {{Symmetry in XPath}}, Url = {http://www.pms.ifi.lmu.de/publikationen/#PMS-FB-2001-16}, Urldate = {2004/11/11}, Year = {2001}, Abstract = {The location path language XPath is of particular importance for XML applications since it is a core component of many XML processing standards such as XSLT or XQuery. In this paper, based on axis symmetry of XPath, equivalences of XPath 1.0 location paths involving ?reverse axes?, such as ancestor and preceding, are established. These equivalences are used as rewriting rules in an algorithm for transforming location paths with reverse axes into equivalent reverse-axis-free ones. Location paths without reverse axes as generated by the presented rewriting algorithm enable efficient SAX-like streamed data processing of XPath.}} @inproceedings{Ono.Koyanagi.ea_XSLTStylesheetGeneration_SAINT_2002, Author = {Ono, Kouichi and Koyanagi, Teruo and Abe, Mari and Hori, Masahiro}, Booktitle = {Proc. Symposium on Applications and the Internet}, Conference-Abbr = {SAINT}, Keywords = {XML XSLT HTML visual stylesheet generation}, Owner = {Tim Furche}, Title = {{XSLT Stylesheet Generation by Example with WYSIWYG Editing}}, Url = {http://doi.ieeecomputersociety.org/10.1109/SAINT.2002.994471}, Year = {2002}, Abstract = {XSLT plays an important role in data conversions between different XML representations. However, besides the transformations between XML data representations, conversion to an HTML document is one of the most practical tasks for XSLT, because it allows XML documents to be rendered in a human-readable form using Web browsers. We have developed XSLbyDemo, which is an XSLT stylesheet generation module to be plugged into a commercially available full-fledged HTML authoring tool. The remarkable feature of XSLbyDemo is that users can create an XSLT stylesheet automatically solely on the basis of their knowledge of HTML editing. We briefly explain situations where stylesheets for XML rendering are needed. We then introduce the rule generation method based on the users' operation history recorded behind the WYSIWYG editor, and in particular explain the ways of generalizing the created rules so that the obtained rules can be applied to other documents slightly different from the original one. Finally, we give a practical example of the rules generation by XSLbyDemo, and demonstrate that our method can be used for not only the conversion but also the partitioning of a real-life HTML document into smaller pages represented with Compact HTML to be rendered on Web-enabled cellular phones such as i-mode phones}} @inproceedings{Onose.Simeon_XQueryatyour_WWW_2004, Author = {Onose, Nicola and Simeon, Jerome}, Booktitle = WWW, Conference-Abbr = {WWW}, Doi = {http://doi.acm.org/10.1145/988672.988754}, Isbn = {1-58113-844-X}, Keywords = {XML XQuery web services implementation}, Location = {New York, NY, USA}, Pages = {603--611}, Pdf = {QueryEvaluation/XML/XQuery/Onose.Simeon_XQueryatyour_WWW_2004.pdf}, Publisher = {ACM Press}, Title = {{XQuery at your Web Service}}, Url = {http://www.www2004.org/proceedings/docs/1p603.pdf}, Year = {2004}, Abstract = {XML messaging is at the heart of Web services, providing the flexibility required for their deployment, composition, and maintenance. Yet, current approaches to Web services development hide the messaging layer behind Java or C# APIs, preventing the application to get direct access to the underlying XML information. To address this problem, we advocate the use of a native XML language, namely XQuery, as an integral part of the Web services development infrastructure. The main contribution of the paper is a binding between WSDL, the Web Services Description Language, and XQuery. The approach enables the use of XQuery for both Web services deployment and composition. We present a simple command-line tool that can be used to automatically deploy a Web service from a given XQuery module, and extend the XQuery language itself with a statement for accessing one or more Web services. The binding provides tight-coupling between WSDL and XQuery, yielding additional benefits, notably: the ability to use WSDL as an interface language for XQuery, and the ability to perform static typing on XQuery programs that include Web service calls. Last but not least, the proposal requires only minimal changes to the existing infrastructure. We report on our experience implementing this approach in the Galax XQuery processor.}} @inproceedings{Paparizos.Al-Khalifa.ea_GroupinginXML_XMLDM_2002, Author = {Paparizos, Stelios and Al-Khalifa, Shurug and Jagadish, H. V. and Lakshmanan, Laks V.S. and Nierman, Andrew and Srivastava, Divesh and Wu, Yuqing}, Booktitle = {EDBT Workshop on XML Data Management}, Conference-Abbr = {XMLDM}, Keywords = {XQuery, grouping, query optimization, algebra, TAX, XML}, Number = {2490}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/XQuery/Grouping/Paparizos.Al-Khalifa.ea_GroupinginXML_XMLDM_2002.pdf}, Publisher = {Springer-Verlag}, Series = {LNCS}, Title = {{Grouping in XML}}, Url = {http://www.cs.indiana.edu/~yuqwu/papers/XMLDB02-Grouping.pdf}, Year = {2002}, Abstract = {XML permits repeated and missing sub-elements, and missing attributes. We discuss the consequent implications on grouping, both with respect to specification and with respect to implementation. The techniques described here have been implemented in the TIMBER native XML database system being developed at the University of Michigan.}} @inproceedings{Paparizos.Wu.ea_TreeLogicalClasses_SIGMOD_2004, Author = {Paparizos, Stelios and Wu, Yuqing and Lakshmanan, Laks V. S. and Jagadish, H. V.}, Booktitle = SIGMOD, Conference-Abbr = {SIGMOD}, Doi = {http://doi.acm.org/10.1145/1007568.1007579}, Isbn = {1-58113-859-8}, Keywords = {XML XQuery optimization tree locical classes efficiency}, Location = {Paris, France}, Pages = {71--82}, Pdf = {QueryEvaluation/XML/XQuery/Paparizos.Wu.ea_TreeLogicalClasses_SIGMOD_2004.pdf}, Publisher = {ACM Press}, Title = {{Tree Logical Classes for Efficient Evaluation of XQuery}}, Url = {http://www.cs.indiana.edu/~yuqwu/papers/SIGMOD04-TLC.pdf}, Year = {2004}, Abstract = {XML is widely praised for its flexibility in allowing repeated and missing sub-elements. However, this flexibility makes it challenging to develop a bulk algebra, which typically manipulates sets of objects with identical structure. A set of XML elements, say of type book, may have members that vary greatly in structure, e.g. in the number of author sub-elements. This kind of heterogeneity may permeate the entire document in a recursive fashion: e.g., different authors of the same or different book may in turn greatly vary in structure. Even when the document conforms to a schema, the flexible nature of schemas for XML still allows such significant variations in structure among elements in a collection. Bulk processing of such heterogeneous sets is problematic.In this paper, we introduce the notion of logical classes (LC) of pattern tree nodes, and generalize the notion of pattern tree matching to handle node logical classes. This abstraction pays off significantly in allowing us to reason with an inherently heterogeneous collection of elements in a uniform, homogeneous way. Based on this, we define a Tree Logical Class (TLC) algebra that is capable of handling the heterogeneity arising in XML query processing, while avoiding redundant work. We present an algorithm to obtain a TLC algebra expression from an XQuery statement (for a large fragment of XQuery). We show how to implement the TLC algebra efficiently, introducing the nest-join as an important physical operator for XML query processing. We show that evaluation plans generated using the TLC algebra not only are simpler but also perform better than those generated by competing approaches. TLC is the algebra used in the Timber [8] system developed at the University of Michigan.}} @inproceedings{Pietriga.Vion-Dury.ea_VXT-VisualApproach_DocEng_2001, Author = {Pietriga, Emmanuel and Vion-Dury, Jean-Yves and Quint, Vincent}, Booktitle = {Proc. ACM Symposium on Document Engineering}, Conference-Abbr = {DocEng}, Doi = {http://doi.acm.org/10.1145/502187.502189}, Isbn = {1-58113-432-0}, Keywords = {XML query languages visual VXT transformer path based}, Location = {Atlanta, Georgia, USA}, Pages = {1--10}, Pdf = {QueryEvaluation/XML/Visualization/Pietriga.Vion-Dury.ea_VXT-VisualApproach_DocEng_2001.pdf}, Publisher = {ACM Press}, Title = {{VXT: a Visual Approach to XML Transformations}}, Url = {http://www.cs.uwm.edu/classes/cs790/digdoc-s2003/papers/p1-pietriga.pdf}, Year = {2001}, Abstract = {The domain of XML transformations is becoming more and more important as a result of the increasing number of applications adopting XML as their format for data exchange or representation. Most of the existing solutions for expressing XML transformations are textual languages, such as XSLT or DOM combined with a general-purpose programming language. Several tools build on top of these languages, providing a graphical environment. Transformations are however still specified in a textual way using the underlying language (often XSLT), thus requiring the user to learn the associated textual language.We believe that visual programming techniques are well-suited to representing XML structures and make the specification of transformations simpler. We present a visual programming language for the specification of XML transformations in an interactive environment, based on a zoomable user interface toolkit. Transformations can be run from the application or exported to two target languages: XSLT and Circus, a general-purpose structure transformation language designed by the second author and briefly introduced in this paper.}} @techreport{Prudhommeaux.Seaborne_SPARQLQueryLanguage_TR_2004, Author = {Prud'hommeaux, Eric and Seaborne, Andy}, Date-Modified = {2006-03-02 17:47:09 +0100}, Institution = {W3C}, Keywords = {RDF Query Evaluation Query Languages}, Owner = {Tim Furche}, Title = {{SPARQL Query Language for RDF}}, Type = {Working Draft}, Url = {http://www.w3.org/TR/rdf-sparql-query/}, Urldate = {2004/12/20}, Year = {2006}, Abstract = {RDF is a flexible, extensible way to represent information about World Wide Web resources. It is used to represent, among other things, personal information, social networks, metadata about digital artifacts like music and images, as well as provide a means of integration over disparate sources of information. A standardized query language for RDF data with multiple implementations offers developers and end users a way to write and to consume the results of queries across this wide range of information. This document describes a query language for RDF, called SPARQL, for querying RDF data. This document describes the query language part of SPARQL for easy access to RDF stores. It is designed to meet the requirements and design objectives described in the W3C RDF Data Access Working Group (DAWG) document "RDF Data Access Use Cases and Requirements".}} @article{Riecken_PersonalizedViewsof_CACM_2000, Author = {Riecken, Doug}, Journal = {Communications of the ACM}, Journal-Abbr = {CACM}, Keywords = {Personalization Web Vision}, Number = {8}, Owner = {Tim Furche}, Pages = {26-28}, Title = {{Personalized Views of Personalization}}, Volume = {43}, Year = {2000}, Abstract = {Our vocabulary of Internet-related words has become socially popular and, of course, an essential tool of trade in the hands of marketing initiatives. I recall in the early 1990s when words like "agent" and "multimedia" were so overused they became little more than meaningless marketing spin.}} @inproceedings{Robie.The-Syntactic-Web.2001, Author = {Robie, Jonathan}, Booktitle = {Proc. XML Conference and Exhibition}, Conference-Abbr = {XML}, Date-Added = {2005-05-01 22:33:35 +0200}, Date-Modified = {2005-05-01 22:34:19 +0200}, Title = {{The Syntactic Web}}, Url = {http://www.idealliance.org/pa pers/xml2001/papers/html/03-01-04.html}, Year = {2001}} @inproceedings{Robie_UpdatesinXQuery_XML_2001, Author = {Robie, Jonathan}, Booktitle = {XML Conference \& Exhibiton}, Conference-Abbr = {XML}, Keywords = {XML XQuery update query languages reactivity}, Owner = {Tim Furche}, Title = {{Updates in XQuery}}, Year = {2001}} @phdthesis{Schaffert_Xcerpt-Rule-BasedQuery_2004, Author = {Schaffert, Sebastian}, Date-Modified = {2006-03-06 17:49:33 +0100}, Keywords = {XML Xcerpt query language semantics syntax simulation unification}, Pdf = {QueryEvaluation/Xcerpt/Schaffert_Xcerpt-Rule-BasedQuery_2004.pdf}, School = {University of Munich}, Title = {{Xcerpt: A Rule-Based Query and Transformation Language for the Web}}, Type = {{Dissertation/Ph.D. thesis}}, Url = {http://www.pms.ifi.lmu.de/publikationen#PMS-DISS-2004-1}, Year = {2004}, Abstract = {This thesis investigates querying the Web and the Semantic Web. It proposes a new rulebased query language called Xcerpt. Xcerpt differs from other query languages in that it uses patterns instead of paths for the selection of data, and in that it supports both rule chaining and recursion. Rule chaining serves for structuring large queries, as well as for designing complex query programs (e.g. involving queries to the Semantic Web), and for modelling inference rules. Query patterns may contain special constructs like partial subqueries, optional subqueries, or negated subqueries that account for the particularly flexible structure of data on the Web. Furthermore, this thesis introduces the syntax of the language Xcerpt, which is illustrated on a large collection of use cases both from the conventional Web and the Semantic Web. In addition, a declarative semantics in form of a Tarski-style model theory is described, and an algorithm is proposed that performs a backward chaining evaluation of Xcerpt programs. This algorithm has also been implemented (partly) in a prototypical runtime system. A salient aspect of this algorithm is the specification of a non-standard unification algorithm called simulation unification that supports the new query constructs described above. This unification is symmetric in the sense that variables in both terms can be bound. On the other hand it is in contrast to standard unification assymmetric in the sense that the unification determines that the one term is a subterm of the other term.}} @inproceedings{Schaffert.Bry_QueryingWebReconsidered_EML_2004, Author = {Schaffert, Sebastian and Bry, Fran{\c c}ois}, Booktitle = {Proc. Extreme Markup Languages}, Conference-Abbr = {EML}, Date-Modified = {2006-03-06 17:48:15 +0100}, Keywords = {REWERSE Xcerpt Query Languages}, Pdf = {SemanticWeb/REWERSE/Schaffert.Bry_QueryingWebReconsidered_EML_2004.pdf.download/Schaffert.Bry_QueryingWebReconsidered_EML_2004.pdf}, Title = {{Querying the Web Reconsidered: A Practical Introduction to Xcerpt}}, Url = {http://www.pms.ifi.lmu.de/publikationen#PMS-FB-2004-7}, Year = {2004}, Abstract = {Anfragesprachen f{\"u}r XML-Daten sind heutzutage wesentliche Werkzeuge in der Entwicklung von Webanwendungen. Die am weitesten verbreiteten Sprachen sind XQuery und XSLT, die beide auf der pfadbasierten Selektionssprache XPath aufbauen. Dieser Vortrag gibt einen Einblick in eine neue Anfragesprache namens Xcerpt, die statt des pfadbasierten Ansatzes Anfragepattern verwendet, welche eine deklarativere Spezifikation von Anfragen erlauben. Xcerpt ist ausserdem eine deduktive, regelbasierte Sprache, die auch die Verkn{\"u}pfung von mehreren Regeln (Chaining) und Rekursion erm{\"o}glicht. Eine Xcerpt-Regel kann damit auch als Abstraktion der Ausgangsdaten verstanden werden, hnlich zu Views in relationalen Datenbanken.Auf Xcerpt aufbauend wird ausserdem die visuelle Anfragesprache visXcerpt vorgestellt. Aufgrund des patternbasierten Ansatzes von Xcerpt k{\"o}nnen in visXcerpt Anfragen auf einfache Weise visuell dargestellt und bearbeitet werden.Das Ziel beider Anfragesprachen ist es, die Entwicklung von Anwendungen insbesondere f{\"u}r das "Semantic Web" zu vereinfachen:Anfnger k{\"o}nnen mit Hilfe von visXcerpt Anfragen schnell und intuitiv formulieren und Fortgeschrittenen hilft die Deklarativitt von Xcerpt bei der Gliederung komplexer Programme.}} @inproceedings{SchenkelTheobald.HOPI-An-Efficient-C.2004, Author = {Schenkel, R. and Theobald, A. and Weikum, G.}, Booktitle = {Proc. Extending Database Technology}, Conference-Abbr = {EDBT}, Date-Added = {2005-05-01 22:42:02 +0200}, Date-Modified = {2005-05-01 22:43:08 +0200}, Title = {{HOPI: An Efficient Connection Index for Complex XML Document Collections}}, Year = {2004}} @inproceedings{Schott.Noga_LazyXSLTransformations_DocEng_2003, Author = {Schott, Steffen and Noga, Markus L.}, Booktitle = {Proc. ACM Symposium on Document Engineering}, Conference-Abbr = {DocEng}, Doi = {http://doi.acm.org/10.1145/958220.958224}, Isbn = {1-58113-724-9}, Keywords = {XML XSLT evaluation lazy query languages processing}, Location = {Grenoble, France}, Pages = {9--18}, Pdf = {QueryEvaluation/XML/XSLT/Schott.Noga_LazyXSLTransformations_DocEng_2003.pdf}, Publisher = {ACM Press}, Title = {{Lazy XSL Transformations}}, Url = {http://portal.acm.org/citation.cfm?id=958224}, Year = {2003}, Abstract = {We introduce a lazy XSLT interpreter that provides random access to the transformation result. This allows efficient pipelining of transformation sequences. Nodes of the result tree are computed only upon initial access. As these computations have limited fan-in, sparse output coverage propagates backwards through the pipeline.In comparative measurements with traditional eager implementations, our approach is on par for complete coverage and excels as coverage becomes sparser. In contrast to eager evaluation, lazy evaluation also admits infinite intermediate results, thus extending the design space for transformation sequences.To demonstrate that lazy evaluation preserves the semantics of XSLT, we reduce XSLT to the lambda calculus via a functional language. While this is possible for all languages, most imperative languages cannot profit from the confluence of lambda as only one reduction applies at a time.}} @inproceedings{Seipel_ProcessingXML-Documentsin_WLP_2002, Author = {Seipel, Dietmar}, Booktitle = {Workshop on Logic Programming}, Conference-Abbr = {WLP}, Keywords = {XML query languages prolog logic programming FnQuery}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/LogicProgrammingApproaches/Seipel_ProcessingXML-Documentsin_WLP_2002.pdf}, Title = {{Processing XML-Documents in Prolog}}, Url = {http://www-info1.informatik.uni-wuerzburg.de/database/papers/wlp_2002.ps.gz}, Year = {2002}} @article{Seipel.Baumeister_DeclarativeMethodsEvaluation_KI_2004, Author = {Seipel, Dietmar and Baumeister, Joachim}, Journal = {KI--K{\"u}nstliche Intelligenz}, Journal-Abbr = {KI}, Keywords = {XML OWL FnQuery ontologies prolog logic programming}, Owner = {Tim Furche}, Pages = {51--57}, Title = {{Declarative Methods for the Evaluation of Ontologies}}, Url = {http://ki.informatik.uni-wuerzburg.de/papers/baumeister/2004/EvalOntologies_KI4_2004.pdf}, Volume = {4}, Year = {2004}, Abstract = {The ontology web language Owl has been established as a standardized representation for knowledge, especially in the context of the semantic web. An important facet of the management of such knowledge bases consists in its evaluation. Besides standard evaluation methods described in the literature particular applications can require to consider further measures. In this paper, we use a declarative, logic-based Xml query and transformation language called FnQuery, which is suitable for fexibly defning queries for evaluating Owl-based knowledge. The queries are evaluated using logic programming and nonmonotonic reasoning systems. The presented approach could be extended to handle complex refactorings as well.}} @inproceedings{Seipel.Baumeister.ea_DeclarativelyQueryingand_INAP_2004, Author = {Seipel, Dietmar and Baumeister, Joachim and Hopfner, Marbod}, Booktitle = {Proc. Intl. Conf. on Applications of Declarative Programming and Knowledge Management}, Conference-Abbr = {INAP}, Keywords = {XML query languages FnQuery visualization logic programming prolog}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/LogicProgrammingApproaches/Seipel.Baumeister.ea_DeclarativelyQueryingand_INAP_2004.pdf}, Title = {{Declaratively Querying and Visualizing Knowledge Bases in XML}}, Url = {http://www-info1.informatik.uni-wuerzburg.de/database/papers/inap_seipel_2004.ps.gz}, Year = {2004}, Abstract = {The maintenance of large knowledge systems usually is a rather complex task. In this paper we will show that extensions or modifications of a knowledge base can be supported by appropriate visualizations techniques, e.g. by illustrating dependencies of the considered knowledge. In particular, we introduce a declarative approach for querying and visualizing rule-based knowledge represented as XML documents; a knowledge engineer can extract and visually inspect parts of the knowledge base by ad-hoc declarations in a flexible manner.}} @inproceedings{Selinger_TopFiveData_ICDE_2005, Author = {Selinger, Pat}, Booktitle = ICDE, Conference-Abbr = {ICDE}, Keywords = {data processing metadata unstructured autonomic speech}, Owner = {Tim Furche}, Title = {{Top Five Data Challenges for the Next Decade}}, Year = {2005}} @book{Simpson_XPathandXPointer_2002, Author = {Simpson, John E.}, Edition = {1st}, Keywords = {XML XPath XPointer querying locating linking query languages}, Owner = {Tim Furche}, Publisher = {O'Reilly}, Title = {{XPath and XPointer}}, Year = {2002}, Abstract = {Referring to specific information inside an XML document is a little like finding a needle in a haystack. XPath and XPointer are two closely related languages that play a key role in XML processing by allowing developers to find these needles and manipulate embedded information. By the time you've finished XPath and XPointer, you'll know how to construct a full XPointer (one that uses an XPath location path to address document content) and completely understand both the XPath and XPointer features it uses.}} @inproceedings{Tane.Schmitz.ea_SemanticresourceManagement_WWW_2004, Author = {Tane, Julien and Schmitz, Christoph and Stumme, Gerd}, Booktitle = WWW, Citeseerurl = {2005/02/15}, Conference-Abbr = {WWW}, Keywords = {Personalization Web E-Learning KAON L3L}, Owner = {Tim Furche}, Pdf = {ApplicationAreas/Personalization/Tane.Schmitz.ea_SemanticresourceManagement_WWW_2004.pdf}, Title = {{Semantic Resource Management for the Web: An E-Learning Application}}, Url = {http://www.l3s.de/php/detail.php?dc_title=+Semantic+resource+Management+for+the+web%3A+An+e-learning+application.&dc_creator=Julien+Tane%2C+Christoph+Schmitz%3B+Gerd+Stumme.}, Year = {2004}, Abstract = {Topics in education are changing with an ever faster pace. ELearning resources tend to be more and more decentralized. Users increasingly need to be able to use the resources of the web. For this, they should have tools for finding and organizing information in a decentralized way. In this paper, we show how an ontologybased tool suite allows to make the most of the resources available on the web.}} @inproceedings{Tatarinov.Halevy_EfficientQueryReformulation_SIGMOD_2004, Author = {Tatarinov, Igor and Halevy, Alon}, Booktitle = SIGMOD, Conference-Abbr = {SIGMOD}, Doi = {http://doi.acm.org/10.1145/1007568.1007629}, Isbn = {1-58113-859-8}, Keywords = {XML XQuery rewriting optimization query evaluation}, Location = {Paris, France}, Pages = {539--550}, Pdf = {QueryEvaluation/XML/XQuery/Tatarinov.Halevy_EfficientQueryReformulation_SIGMOD_2004.pdf}, Publisher = {ACM Press}, Title = {{Efficient Query Reformulation in peer Data Management Systems}}, Url = {http://data.cs.washington.edu/papers/piazza-sigmod2004.pdf}, Year = {2004}, Abstract = {Peer data management systems (PDMS) offer a flexible architecture for decentralized data sharing. In a PDMS, every peer is associated with a schema that represents the peer's domain of interest, and semantic relationships between peers are provided locally between pairs (or small sets) of peers. By traversing semantic paths of mappings, a query over one peer can obtain relevant data from any reachable peer in the network. Semantic paths are traversed by reformulating queries at a peer into queries on its neighbors.Naively following semantic paths is highly inefficient in practice. We describe several techniques for optimizing the reformulation process in a PDMS and validate their effectiveness using real-life data sets. In particular, we develop techniques for pruning paths in the reformulation process and for minimizing the reformulated queries as they are created. In addition, we consider the effect of the strategy we use to search through the space of reformulations. Finally, we show that pre-computing semantic paths in a PDMS can greatly improve the efficiency of the reformulation process. Together, all of these techniques form a basis for scalable query reformulation in PDMS.To enable our optimizations, we developed practical algorithms, of independent interest, for checking containment and minimization of XML queries, and for composing XML mappings.}} @book{Tennison_XSLTandXPath_2001, Author = {Tennison, Jeni}, Keywords = {XML XSLT XPath query languages}, Owner = {Tim Furche}, Publisher = {John Wiley}, Title = {{XSLT and XPath On The Edge}}, Year = {2001}, Abstract = {Extensible Stylesheet Language Transformations, along with the XML Path Language, give you the power to transform XML documents into HTML documents, or to other XML documents that you can use in Web-based applications. But how do you implement XSLT in the real world? This book provides the answers. Covering everything from reformatting numbers to creating dynamic XSLT applications, XSLT expert Jeni Tennison delivers a wealth of ready-to-use utility templates and practical XSLT solutions -- everything you need to jump-start XSLT development.}} @inproceedings{Theobald.Weikum_XXLSearchEngine_SIGMOD_2002, Author = {Theobald, Anja and Weikum, Gerhard}, Booktitle = SIGMOD, Conference-Abbr = {SIGMOD}, Doi = {http://doi.acm.org/10.1145/564691.564768}, Isbn = {1-58113-497-5}, Keywords = {XML ranking IR information retrieval query languages}, Location = {Madison, Wisconsin}, Pages = {615--615}, Publisher = {ACM Press}, Title = {{The XXL Search Engine: Ranked Retrieval of XML Data using Indexes and Ontologies}}, Year = {2002}} @inproceedings{Tozawa_TowardsStaticType_DocEng_2001, Author = {Tozawa, Akihiko}, Booktitle = {Proc. ACM Symposium on Document Engineering}, Conference-Abbr = {DocEng}, Doi = {http://doi.acm.org/10.1145/502187.502191}, Isbn = {1-58113-432-0}, Keywords = {XML XSLT type checking query languages}, Location = {Atlanta, Georgia, USA}, Pages = {18--27}, Publisher = {ACM Press}, Title = {{Towards Static Type Checking for XSLT}}, Url = {http://wam.inrialpes.fr/people/roisin/mw2004/Tozawa2001.pdf}, Year = {2001}} @inproceedings{Trombetta.Montesi_EquivalencesandOptimizations_IDEAS_2004, Author = {Trombetta, Alberto and Montesi, Danilo}, Booktitle = {Proc. Intl. Database Engineering and Applications Symposium}, Conference-Abbr = {IDEAS}, Keywords = {XML XSLT query languages optimization equivalence}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/XML/XSLT/Trombetta.Montesi_EquivalencesandOptimizations_IDEAS_2004.pdf}, Title = {{Equivalences and Optimizations in an Expressive XSLT Fragment}}, Url = {http://csdl.computer.org/dl/proceedings/ideas/2004/2168/00/21680171.pdf}, Year = {2004}, Abstract = {XML is the standard data interchange format and XSLT is the W3C proposed standard for transforming and restructuring XML documents. It turns out that XSLT has very powerful query capabilities as well. However, due to its complex syntax and lack of formal specification, it is not a trivial task to decide whether two XSLT stylesheets yield the same result, even if for an XSLT fragment. We isolate such fragment, powerful enough for expressing several interesting queries and for manipulating XML documents and show how to translate them into queries expressed in a properly extended version of TAX, a powerful XML query algebra, for which we provide a collection of equivalence rules. It is then possible to reason about XSLT equivalences, by translating XSLT queries into XTAX queries and then statically verifying their equivalence, by means of the mentioned equivalence rules.}} @inproceedings{Villard.Layaida_IncrementalXSLTTransformation_WWW_2002, Author = {Villard, Lionel and Laya{\"\i}da, Nabil}, Booktitle = WWW, Conference-Abbr = {WWW}, Doi = {http://doi.acm.org/10.1145/511446.511508}, Isbn = {1-58113-449-5}, Keywords = {XML XSLT incremental query evaluation languages}, Location = {Honolulu, Hawaii, USA}, Pages = {474--485}, Pdf = {QueryEvaluation/XML/XSLT/Villard.Layaida_IncrementalXSLTTransformation_WWW_2002.pdf}, Publisher = {ACM Press}, Title = {{An Incremental XSLT Transformation Processor for XML Document Manipulation}}, Url = {http://www.research.ibm.com/people/v/villard/Papiers/incXSLT.pdf}, Year = {2002}, Abstract = {In this paper, we present an incremental transformation framework called incXSLT. This framework has been experimented for the XSLT language defined at the World Wide Web Consortium. For the currently available tools, designing the XML content and the transformation sheets is an inefficient, a tedious and an error prone experience. Incremental transformation processors such as incXSLT represent a better alternative to help in the design of both the content and the transformation sheets. We believe that such frameworks are a first step toward fully interactive transformation-based authoring environments.}} @inproceedings{Walsh.RDF-Twig-accessing-.2003, Author = {Walsh, Norman}, Booktitle = {Proc. Extreme Markup Languages}, Conference-Abbr = {EML}, Date-Added = {2005-05-01 22:37:01 +0200}, Date-Modified = {2005-05-01 22:38:48 +0200}, Title = {{RDF Twig: accessing RDF graphs in XSLT}}, Url = {http://www.mulberrytech.com/Extreme/Proceedings/xslfo-pdf/2003/Walsh01/EML2003Walsh01.pdf}, Year = {2003}} @book{Walsh.Muellner_DocBook-DefinitiveGuide_1999, Author = {Walsh, Norman and Muellner, Leonard}, Owner = {Tim Furche}, Publisher = {O?Reilly}, Title = {{DocBook: The Definitive Guide}}, Url = {http://www.oreilly.com/catalog/docbook/}, Year = {1999}, Abstract = {DocBook is a Document Type Definition (DTD) for use with XML (the Extensible Markup Language) and SGML (the Standard Generalized Markup Language). DocBook lets authors in technical groups exchange and reuse technical information. This book contains an introduction to SGML, XML, and the DocBook DTD, plus the complete reference information for DocBook.}} @inproceedings{Wan.Dobbie_MiningAssociationRules_CRPIT_2004, Author = {Wan, Jacky W. W. and Dobbie, Gillian}, Booktitle = {Proc. Workshop on Australasian Information Security, Data Mining Web Intelligence, and Software Internationalisation}, Conference-Abbr = {CRPIT}, Keywords = {XML XQuery mining assocation rules}, Location = {Dunedin, New Zealand}, Pages = {169--174}, Publisher = {Australian Computer Society, Inc.}, Title = {{Mining Association Rules from XML data using XQuery}}, Url = {http://crpit.com/confpapers/CRPITV32Wan.pdf}, Year = {2004}, Abstract = {In recent years XML has became very popular for representing semistructured data and a standard for data exchange over the web. Mining XML data from the web is becoming increasingly important. Several encouraging attempts at developing methods for mining XML data have been proposed. However, efficiency and simplicity are still a barrier for further development. Normally, pre-processing or post-processing are required for mining XML data, such as transforming the data from XML format to relational format. In this paper, we show that extracting association rules from XML documents without any pre-processing or post-processing using XQuery is possible and analyze the XQuery implementation of the well-known Apriori algorithm. In addition, we suggest features that need to be added into XQuery in order to make the implementation of the Apriori algorithm more efficient.}} @inproceedings{Waworuntu.Bailey_XSLTGen-SystemAutomatically_ER_2004, Author = {Waworuntu, Stella and Bailey, James}, Booktitle = {Proc. Intl. Conf. on Conceptual Modeling}, Conference-Abbr = {ER}, Keywords = {XML XSLT generation semantic query languages}, Owner = {Tim Furche}, Title = {{XSLTGen: A System for Automatically Generating XML Transformations via Semantic Mappings}}, Url = {http://www.cs.mu.oz.au/~jbailey/papers/xsltgen.ps}, Year = {2004}, Abstract = {XML is rapidly emerging as a dominant standard for representing and exchanging information. The ability to transform and present data in XML is crucial and XSLT (Extensible stylesheet transformations) is a relatively recent programming language, specially designed to support this activity. Despite its utility, however, XSLT is widely considered a difficult language to learn. In this paper, we present a novel system called XSLTGen, an automatic XSLT Generator. This system automatically generates an XSLT program, given a source XML document and a desired output HTML or XML document. It allows users to become familiar with and learn XSLT programs, based solely on their knowledge of XML or HTML. Our method for automatically generating XSLT transformations is based on the use of semantic mappings between the input and output documents. We show how such mappings can be first discovered and then employed to create XSLT programs. The results of our experiments show that XSLTGen works well with a number of different varieties of XML and HTML documents.}} @article{Wiegand_InvestigatingXQueryQuerying_SIGMOD_2002, Author = {Wiegand, Nancy}, Doi = {http://doi.acm.org/10.1145/565117.565122}, Issn = {0163-5808}, Journal = {SIGMOD Record}, Journal-Abbr = {SIGMOD}, Keywords = {XML XQuery relational databases heterogenity}, Number = {2}, Pages = {28--33}, Pdf = {QueryEvaluation/XML/XQuery/Wiegand_InvestigatingXQueryQuerying_SIGMOD_2002.pdf}, Publisher = {ACM Press}, Title = {{Investigating XQuery for Querying across Database Object Types}}, Url = {http://portal.acm.org/citation.cfm?id=565122}, Volume = {31}, Year = {2002}, Abstract = {In addition to facilitating querying over the Web, XML query languages may provide high level constructs for useful facilities in traditional DBMSs that do not currently exist. In particular, current DBMS query languages do not allow querying across database object types to yield heterogeneous results. This paper motivates the usefulness of heterogeneous querying in traditional DBMSs and investigates XQuery, an emerging standard for XML query languages, to express such queries. The usefulness of querying and storing heterogeneous types is also applied to XML data within a Web information system.}} @inproceedings{Wood_OnEquivalenceof_CL_2000, Author = {Wood, Peter T.}, Booktitle = {Proc. Intl. Conf. on Computational Logic}, Conference-Abbr = {CL}, Isbn = {3-540-67797-6}, Keywords = {XML XPath query containment fragment equivalence}, Pages = {1152--1166}, Publisher = {Springer-Verlag}, Title = {{On the Equivalence of XML Patterns}}, Year = {2000}} @inproceedings{Zaniolo_DatabaseLanguageGEM_SIGMOD_1983, Author = {Zaniolo, Carlo}, Booktitle = SIGMOD, Conference-Abbr = {SIGMOD}, Keywords = {Query languages GEM path expressions QUEL}, Owner = {Tim Furche}, Pdf = {QueryEvaluation/Languages/Zaniolo_DatabaseLanguageGEM_SIGMOD_1983.pdf}, Title = {{The Database Language GEM}}, Url = {http://www.cs.ucla.edu/%7Ezaniolo/papers/sigmod83.pdf}, Year = {1983}, Abstract = {GEM (bn acronym for General Entity Manipulator) is a general-purpose query and update language for the DSIS data model, which is a semantic data model of the Entity-Relationship type. GEM is designed as an easy-to-use extension of the relational language QUEL. providing supporr for. the notions of entities with surrogates, aggregation, generalization, null values, and set-valued attributes.}} @inproceedings{Zhang.Dimitrova.ea_Rainbow-multi-XQueryOptimization_SIGMOD_2003, Author = {Zhang, Xin and Dimitrova, Katica and Wang, Ling and Sayed, Maged El and Murphy, Brian and Pielech, Bradford and Mulchandani, Mukesh and Ding, Luping and Rundensteiner, Elke A.}, Booktitle = SIGMOD, Conference-Abbr = {SIGMOD}, Doi = {http://doi.acm.org/10.1145/872757.872861}, Isbn = {1-58113-634-X}, Keywords = {XML XQuery view-based query optimization evalution processing}, Location = {San Diego, California}, Pages = {671--671}, Pdf = {QueryEvaluation/XML/XQuery/Zhang.Dimitrova.ea_Rainbow-multi-XQueryOptimization_SIGMOD_2003.pdf}, Publisher = {ACM Press}, Title = {{Rainbow: multi-XQuery Optimization using Materialized XML Views}}, Url = {http://www.cs.wpi.edu/~lisading/docs/demo.pdf}, Year = {2003}} @inproceedings{Zhang.Pielech.ea_HoneyIshrunk_WIDM_2002, Author = {Zhang, Xin and Pielech, Bradford and Rundesnteiner, Elke A.}, Booktitle = {Proc. International Workshop on Web Information and Data Management}, Conference-Abbr = {WIDM}, Doi = {http://doi.acm.org/10.1145/584931.584936}, Isbn = {1-58113-593-9}, Location = {McLean, Virginia, USA}, Pages = {15--22}, Publisher = {ACM Press}, Title = {{Honey, I shrunk the XQuery!: an XML Algebra Optimization Approach}}, Url = {http://davis.wpi.edu/~dsrg/rainbow/RainbowCore/document/xinz-widm-2002-XAT-cleanup.ppt}, Year = {2002}, Abstract = {Mapping of XML data into and out of relational database systems, including query processing over such virtual XML views that wrap relational sources, has become a topic of critical importance recently. The Rainbow XML data management system, being developed at WPI, focuses on the processing and optimization of XQuery queries against XML views over relational data. For this, Rainbow?s query model, the XML Algebra Tree (XAT), has been designed. Because the XML formatting operators are interleaved with the computation operators, this XAT must first be optimized before being translated into SQL. Our computation pushdown technology handles this optimization by splitting the XAT into the XML-specific and SQL-doable operators, with the later then being converted into SQL statements. However, the XAT after computation pushdown may contain unreferenced columns or unused operators. We show that these unneeded operators cannot be discovered by the relational engine after SQL generation. Leaving these operators in the tree would create unnecessarily large SQL statements that will slow down the overall execution. Our main contributions to XML query processing, described in this paper, are threefold. One, we describe the XAT algebra for modeling XQuery expressions. Two, we propose rewriting rules to optimize XQueries by canceling operators. Three, we describe a cutting algorithm that removes unreferenced columns and operators from the XATs. The techniques discussed in this paper have been successfully implemented in the Rainbow system.}} @inproceedings{Zloof_QueryByExample_AFIPS_1975, Author = {Zloof, Mosh{\'e} M.}, Booktitle = {AFIPS National Computer Conference}, Conference-Abbr = {AFIPS}, Keywords = {QBE relational query languages}, Owner = {Tim Furche}, Title = {{Query By Example}}, Year = {1975}} @book{ODMG_ObjectDataStandard_2000, Editor = {R. G. G. Cattell and Douglas K. Barry and Mark Berler and Jeff Eastman and David Jordan and Craig Russell and Olaf Schadow and Torsten Stanienda and Fernando Velez}, Keywords = {OQL ODMG standard object-oriented database query languages}, Owner = {Tim Furche}, Publisher = {Morgan Kaufmann}, Title = {{Object Data Standard: ODMG 3.0}}, Year = {2000}} @book{ParkHunting.XML-Topic-Maps-Creating.2002, Address = {Boston, MA, USA}, Date-Modified = {2005-04-12 22:24:09 +0200}, Editor = {Jack Park and Sam Hunting}, Isbn = {0201749602}, Publisher = {Addison-Wesley Longman Publishing Co., Inc.}, Title = {{XML Topic Maps: Creating and Using Topic Maps for the Web}}, Year = {2002}} @comment{BibDesk Smart Groups{ conditions comparison 2 key Keywords value identity comparison 2 key Keywords value duplicate conjunction 1 group name Identity, Multirelations, etc. }}