Comparative Evaluation of XML Information Retrieval Systems

This book constitutes the thoroughly refereed post-proceedings of the 5th International Workshop of the Initiative for the Evaluation of XML Retrieval, INEX 2006, held at Dagstuhl Castle, Germany, in December 2006. The papers are organized in topical sections on methodology and seven additional tracks on ad-hoc, natural language processing, heterogeneous collection, multimedia, interactive, use case, as well as document mining.

This book constitutes the thoroughly refereed post-proceedings of the 5th International Workshop of the Initiative for the Evaluation of XML Retrieval, INEX 2006, held at Dagstuhl Castle, Germany, in December 2006. The papers are organized in topical sections on methodology and seven additional tracks on ad-hoc, natural language processing, heterogeneous collection, multimedia, interactive, use case, as well as document mining.

Methodology.- Overview of INEX 2006.- The Wikipedia XML Corpus.- INEX 2006 Evaluation Measures.- Choosing an Ideal Recall-Base for the Evaluation of the Focused Task: Sensitivity Analysis of the XCG Evaluation Measures.- Ad Hoc Track.- A Method of Preferential Unification of Plural Retrieved Elements for XML Retrieval Task.- CISR at INEX 2006.- Compact Representations in XML Retrieval.- CSIRO’s Participation in INEX 2006.- Dynamic Element Retrieval in a Semi-structured Collection.- Efficient, Effective and Flexible XML Retrieval Using Summaries.- Evaluating Structured Information Retrieval and Multimedia Retrieval Using PF/Tijah.- EXTIRP: Baseline Retrieval from Wikipedia.- Filtering and Clustering XML Retrieval Results.- GPX - Gardens Point XML IR at INEX 2006.- IBM HRL at INEX 06.- Indexing “Reading Paths” for a Structured Information Retrieval at INEX 2006.- Influence Diagrams and Structured Retrieval: Garnata Implementing the SID and CID Models at INEX’06.- Information Theoretic Retrieval with Structured Queries and Documents.- SIRIUS XML IR System at INEX 2006: Approximate Matching of Structure and Textual Content.- Structured Content-Only Information Retrieval Using Term Proximity and Propagation of Title Terms.- Supervised and Semi-supervised Machine Learning Ranking.- The University of Kaiserslautern at INEX 2006.- TopX – AdHoc Track and Feedback Task.- Tuning and Evolving Retrieval Engine by Training on Previous INEX Testbeds.- Using Language Models and the HITS Algorithm for XML Retrieval.- Using Topic Shifts in XML Retrieval at INEX 2006.- XSee: Structure Xposed.- Natural Language Processing Track.- Shallow Parsing of INEX Queries.- Using Rich Document Representation in XML Information Retrieval.- NLPX at INEX 2006.- Heterogeneous Collection Track.- The Heterogeneous Collection Track at INEX 2006.- Probabilistic Retrieval Approaches for Thorough and Heterogeneous XML Retrieval.- Multimedia Track.- The INEX 2006 Multimedia Track.- Fusing Visual and Textual Retrieval Techniques to Effectively Search Large Collections of Wikipedia Images.- Social Media Retrieval Using Image Features and Structured Text.- XFIRM at INEX 2006. Ad-Hoc, Relevance Feedback and MultiMedia Tracks.- Interactive Track.- The Interactive Track at INEX 2006.- Use Case Track.- XML-IR Users and Use Cases.- A Taxonomy for XML Retrieval Use Cases.- What XML-IR Users May Want.- Document Track.- Report on the XML Mining Track at INEX 2005 and INEX 2006.- Classifying XML Documents Based on Structure/Content Similarity.- Document Mining Using Graph Neural Network.- Evaluating the Performance of XML Document Clustering by Structure Only.- FAT-CAT: Frequent Attributes Tree Based Classification.- Unsupervised Classification of Text-Centric XML Document Collections.- XML Document Mining Using Contextual Self-organizing Maps for Structures.- XML Document Transformation with Conditional Random Fields.- XML Structure Mapping.