Advances in Multilingual and Multimodal Information Retrieval

The eighth campaign of the Cross Language Evaluation Forum (CLEF) for - ropean languages was held from January to September 2007. There were seven distinct evaluation tracks in CLEF 2007, designed to test the performance of a wide range of multilingual information access systems or system components. CLEF is by now an established international evaluation initiative and, in 2007, 81 groups from all over the world submitted results for one or more of the di?erent evaluation tracks. Full details regarding the design of the tracks, the methodologies used for evaluation, and the results obtained by the participants can be found in the di?erent sections of these proceedings. As always the results of the campaign were reported and discussed at the annual workshop, held in Budapest, Hungary, 19-21 September, immediately following the eleventh European Conference on Digital Libraries. The workshop playsanimportantrolebyprovidingtheopportunityforallthe groupsthathave participated in the evaluation campaign to get together to compare approaches and exchange ideas.

Klappentext
This book constitutes the thoroughly refereed proceedings of the 8th Workshop of the Cross-Language Evaluation Forum, CLEF 2007, held in Budapest, Hungary, September 2007. The revised and extended papers were carefully reviewed and selected for inclusion in the book. There are 115 contributions in total and an introduction. The seven distinct evaluation tracks in CLEF 2007, are designed to test the performance of a wide range of multilingual information access systems or system components. The papers are organized in topical sections on Multilingual Textual Document Retrieval (Ad Hoc), Domain-Specific Information Retrieval (Domain-Specific), Multiple Language Question Answering (QA@CLEF), cross-language retrieval in image collections (Image CLEF), cross-language speech retrieval (CL-SR), multilingual Web retrieval (WebCLEF), cross-language geographical retrieval (GeoCLEF), and CLEF in other evaluations.

Inhalt
What Happened in CLEF 2007.- I: Multilingual Textual Document Retrieval (Ad Hoc).- CLEF 2007: Ad Hoc Track Overview.- Charles University at CLEF 2007 Ad-Hoc Track.- Stemming Approaches for East European Languages.- Applying Query Expansion Techniques to Ad Hoc Monolingual Tasks with the IR-n System.- Bulgarian, Hungarian and Czech Stemming Using YASS.- Sampling Precision to Depth 10000 at CLEF 2007.- Disambiguation and Unknown Term Translation in Cross Language Information Retrieval.- Cross-Language Retrieval with Wikipedia.- Cross-Lingual Information Retrieval System for Indian Languages.- Bengali, Hindi and Telugu to English Ad-Hoc Bilingual Task at CLEF 2007.- Bengali and Hindi to English CLIR Evaluation.- Improving Recall for Hindi, Telugu, Oromo to English CLIR.- Hindi to English and Marathi to English Cross Language Information Retrieval Evaluation.- Amharic-English Information Retrieval with Pseudo Relevance Feedback.- Indonesian-English Transitive Translation for Cross-Language Information Retrieval.- Robust Retrieval Experiments at the University of Hildesheim.- SINAI at CLEF Ad-Hoc Robust Track 2007: Applying Google Search Engine for Robust Cross-Lingual Retrieval.- Improving Robustness Using Query Expansion.- English-to-French CLIR: A Knowledge-Light Approach through Character N-Grams Alignment.- MIRACLE Progress in Monolingual Information Retrieval at Ad-Hoc CLEF 2007.- II: Domain-Specific Information Retrieval (Domain-Specific).- The Domain-Specific Track at CLEF 2007.- The XTRIEVAL Framework at CLEF 2007: Domain-Specific Track.- Query Translation through Dictionary Adaptation.- Experiments in Classification Clustering and Thesaurus Expansion for Domain Specific Cross-Language Retrieval.- Domain-Specific IR for German, English and Russian Languages.- III: Multiple Language Question Answering (QA@CLEF).- Overview of the CLEF 2007 Multilingual Question Answering Track.- Overview of the Answer Validation Exercise 2007.- Overview of QAST 2007.- Question Answering with Joost at CLEF 2007.- What Happened to Esfinge in 2007?.- Coreference Resolution for Questions and Answer Merging by Validation.- Multilingual Question Answering through Intermediate Translation: LCC's PowerAnswer at QA@CLEF 2007.- RACAI's Question Answering System at QA@CLEF2007.- DFKI-LT at QA@CLEF 2007.- University of Wolverhampton at CLEF 2007.- Bilingual Question Answering Using CINDI_QA at QA@CLEF 2007.- The University of Évora's Participation in QA@CLEF-2007.- Web-Based Anaphora Resolution for the QUASAR Question Answering System.- A Lexical Approach for Spanish Question Answering.- Finding Answers Using Resources in the Internet.- UAIC Romanian QA System for QA@CLEF.- The University of Amsterdam's Question Answering System at QA@CLEF 2007.- Combining Wikipedia and Newswire Texts for Question Answering in Spanish.- QA@L2F, First Steps at QA@CLEF.- Priberam's Question Answering System in QA@CLEF 2007.- Combining Logic and Aggregation for Answer Selection.- On the Application of Lexical-Syntactic Knowledge to the Answer Validation Exercise.- Combining Lexical Information with Machine Learning for Answer Validation at QA@CLEF 2007.- Using Recognizing Textual Entailment as a Core Engine for Answer Validation.- A Supervised Learning Approach to Spanish Answer Validation.- UAIC Participation at AVE 2007.- UNED at Answer Validation Exercise 2007.- Adapting QA Components to Mine Answers in Speech Transcripts.- The LIMSI Participation in the QAst Track.- Robust Question Answering for Speech Transcripts Using Minimal Syntactic Analysis.- IV: Cross-Language Retrieval in Image Collections (ImageCLEF).- Overview of the ImageCLEFphoto 2007 Photographic Retrieval Task.- Overview of the ImageCLEF 2007 Object Retrieval Task.- Overview of the ImageCLEFmed 2007 Medical Retrieval and Medical Annotation Tasks.- FIRE in ImageCLEF 2007: Support Vector Machines and Logistic Models to Fuse Image Descriptors for Photo Retrieval.- MIRACLE at ImageCLEFphoto 2007: Evaluation of Merging Strategies for Multilingual and Multimedia Information Retrieval.- Using an Image-Text Parallel Corpus and the Web for Query Expansion in Cross-Language Image Retrieval.- SINAI System: Combining IR Systems at ImageCLEFPhoto 2007.- Multimodal Retrieval by TextSegment Biclustering.- Analysing an Approach to Information Retrieval of Visual Descriptions with IR-n, a System Based on Passages.- DCU and UTA at ImageCLEFPhoto 2007.- Cross-Language and Cross-Media Image Retrieval: An Empirical Study at ImageCLEF2007.- Towards Annotation-Based Query and Document Expansion for Image Retrieval.- Content-Based Image Retrieval Using Combined 2D Attribute Pattern Spectra.- Text-Based Clustering of the ImageCLEFphoto Collection for Augmenting the Retrieved Results.- Trans-Media Pseudo-Relevance Feedback Methods in Multimedia Retrieval.- Cue Integration for Medical Image Annotation.- Multiplying Concept Sources for Graph Modeling.- MIRACLE at ImageCLEFmed 2007: Merging Textual and Visual Strategies to Improve Medical Image Retrieval.- MIRACLE at ImageCLEFanot 2007: Machine Learning Experiments on Medical Image Annotation.- Integrating MeSH Ontology to Improve Medical Information Retrieval.- Speeding Up IDM without Degradation of Retrieval Quality.- Content-Based Medical Image Retrieval Using Low-Level Visual Features and Modality Identification.- Medical Image Retrieval and Automatic Annotation: OHSU at ImageCLEF 2007.- Using Bayesian Network for Conceptual Indexing: Application to Medical Document Indexing with UMLS Metathesaurus.- Baseline Results for the ImageCLEF 2007 Medical Automatic Annotation Task Using Global Image Features.- Evaluation of Automatically Assigned MeSH Terms for Retrieval of Medical Images.- University and Hospitals of Geneva Participating at ImageCLEF 2007.- An Interactive and Dynamic Fusion-Based Image Retrieval Approach by CINDI.- Using Pseudo-Relevance Feedback to Improve Image Retrieval Results.- V: Cross-Language…