Advances in Information Retrieval

1. Front Matter

   PDF

2. Keynote Papers

   1. From Information Retrieval to Information Interaction

      • Gary Marchionini

      Pages 1-11

   2. IR and AI: Traditions of Representation and Anti-representation in Information Processing

      • Yorick Wilks

      Pages 12-26

3. User Studies

   1. A User-Centered Approach to Evaluating Topic Models

      • Diane Kelly, Fernando Diaz, Nicholas J. Belkin, James Allan

      Pages 27-41

   2. A Study of User Interaction with a Concept-Based Interactive Query Expansion Support Tool

      • Hideo Joho, Mark Sanderson, Micheline Beaulieu

      Pages 42-56

   3. Searcher’s Assessments of Task Complexity for Web Searching

      • David J. Bell, Ian Ruthven

      Pages 57-71

4. Question Answering

   1. Evaluating Passage Retrieval Approaches for Question Answering

      • Ian Roberts, Robert Gaizauskas

      Pages 72-84

   2. Identification of Relevant and Novel Sentences Using Reference Corpus

      • Hsin-Hsi Chen, Ming-Feng Tsai, Ming-Hung Hsu

      Pages 85-98

   3. Answer Selection in a Multi-stream Open Domain Question Answering System

      • Valentin Jijkoun, Maarten de Rijke

      Pages 99-111

5. Information Models

   1. A Bidimensional View of Documents for Text Categorisation

      • Giorgio Maria Di Nunzio

      Pages 112-126

   2. Query Difficulty, Robustness, and Selective Application of Query Expansion

      • Giambattista Amati, Claudio Carpineto, Giovanni Romano

      Pages 127-137

   3. Combining CORI and the Decision-Theoretic Approach for Advanced Resource Selection

      • Henrik Nottelmann, Norbert Fuhr

      Pages 138-153

   4. Predictive Top-Down Knowledge Improves Neural Exploratory Bottom-Up Clustering

      • Chihli Hung, Stefan Wermter, Peter Smith

      Pages 154-166

6. Classification

   1. Contextual Document Clustering

      • Vladimir Dobrynin, David Patterson, Niall Rooney

      Pages 167-180

   2. Complex Linguistic Features for Text Classification: A Comprehensive Study

      • Alessandro Moschitti, Roberto Basili

      Pages 181-196

   3. Eliminating High-Degree Biased Character Bigrams for Dimensionality Reduction in Chinese Text Categorization

      • Dejun Xue, Maosong Sun

      Pages 197-208

7. Summarization

   1. Broadcast News Gisting Using Lexical Cohesion Analysis

      • Nicola Stokes, Eamonn Newman, Joe Carthy, Alan F. Smeaton

      Pages 209-222

   2. From Text Summarisation to Style-Specific Summarisation for Broadcast News

      • Heidi Christensen, BalaKrishna Kolluru, Yoshihiko Gotoh, Steve Renals

      Pages 223-237

8. Image Retrieval

   1. Relevance Feedback for Cross Language Image Retrieval

      • Paul Clough, Mark Sanderson

      Pages 238-252

   2. NN^k Networks for Content-Based Image Retrieval

      • Daniel Heesch, Stefan Rüger

      Pages 253-266

Theseproceedingscontaintherefereedfulltechnicalpaperspresentedatthe26th Annual European Conference on Information Retrieval (ECIR 2004). ECIR is theannualconferenceoftheBritishComputerSociety’sspecialistgroupinInf- mation Retrieval. This year the conference was held at the School of Computing and Technology at the University of Sunderland. ECIR began life as the - nual Colloquium on Information Retrieval Research. The colloquium was held in the UK each year until 1998 when the event was held in Grenoble, France. Since then the conference venue has alternated between the United Kingdom and Continental Europe, and the event was renamed the European Conference on Information Retrieval. In recent years, ECIR has continued to grow and has become the major European forum for the discussion of research in the ?eld of Information Retrieval. To mark this metamorphosis from a small informal c- loquium to a major event in the IR research calendar, the BCS-IRSG decided to rename the event to the European Conference on Information Retrieval. ECIR2004received88fullpapersubmissions,fromacrossEuropeandfurther a?eldincludingNorthAmerica,ChinaandAustralia,atestamenttothegrowing popularity and reputation of the conference. Out of the 88 submitted papers, 28 were accepted for presentation. All papers were reviewed by at least three reviewers. Among the accepted papers 11 have a student as the primary author, illustrating that the traditional student focus of the original colloquium is alive today.

• DOM
• Extensible Markup Language (XML)
• Performance
• architecture
• categorization
• classification
• clustering
• collaborative filtering
• complexity
• document retrieval
• hypermedia
• image retrieval
• information retrieval
• proving
• video retrieval

• School of Computing and Technology, David Goldman Informatics Centre, University of Sunderland, Sunderland, UK

  Sharon McDonald

• School of Computing and Technology, University of Sunderland, Sunderland, United Kingdom

  John Tait

Policies and ethics