Abstract
We used a flexible XML retrieval system for evaluating structured document retri eval and multimedia retrieval tasks in the context of the INEX 2006 benchmarks. We investigated the differences between article and element retrieval for Wikipe dia data as well as the influence of an elements context on its ranking. We foun d that article retrieval performed well on many tasks and that pinpointing the r elevant passages inside an article may hurt more than it helps. We found that fo r finding images in isolation the associated text is a very good descriptor in t he Wikipedia collection, but we were not very succesful at identifying relevant multimedia fragments consisting of a combination of text and images.
Original language | Undefined |
---|---|
Title of host publication | Comparative Evaluation of XML Information Retrieval Systems, 5th International Workshop of the Initiative for the Evaluation of XML Retrieval, INEX 2006 |
Editors | N. Fuhr, M Lalmas, A. Trotman |
Place of Publication | Berlin |
Publisher | Springer |
Pages | 104-114 |
Number of pages | 11 |
ISBN (Print) | 978-3-540-73887-9 |
DOIs | |
Publication status | Published - 2007 |
Event | 5th International Workshop of the Initiative for the Evaluation of XML Retrieval, INEX 2006 - Dagstuhl, Germany Duration: 17 Dec 2006 → 20 Dec 2006 Conference number: 5 |
Publication series
Name | Lecture Notes in Computer Science |
---|---|
Publisher | Springer Verlag |
Number | LNCS4549 |
Volume | 4518 |
Workshop
Workshop | 5th International Workshop of the Initiative for the Evaluation of XML Retrieval, INEX 2006 |
---|---|
Abbreviated title | INEX |
Country/Territory | Germany |
City | Dagstuhl |
Period | 17/12/06 → 20/12/06 |
Keywords
- EWI-10816
- DB-XMLIR: XML INFORMATION RETRIEVAL
- METIS-241810
- XML Retrieval
- IR-64261