WikiTranslate: Query Translation for Cross-lingual Information Retrieval using only Wikipedia

Dong Nguyen, Arnold Overwijk, Claudia Hauff, Dolf R.B. Trieschnigg, Djoerd Hiemstra, Franciska de Jong

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

34 Citations (Scopus)
92 Downloads (Pure)

Abstract

This paper presents WikiTranslate, a system which performs query translation for cross-lingual information retrieval (CLIR) using only Wikipedia to obtain translations. Queries are mapped to Wikipedia concepts and the corresponding translations of these concepts in the target language are used to create the final query. WikiTranslate is evaluated by searching with topics formulated in Dutch, French and Spanish in an English data collection. The system achieved a performance of 67% compared to the monolingual baseline.
Original languageEnglish
Title of host publicationEvaluating Systems for Multilingual and Multimodal Information Access
Subtitle of host publication9th Workshop of the Cross-Language Evaluation Forum, CLEF 2008, Aarhus, Denmark, September 17-19, 2008, Revised Selected Papers
EditorsCarol Peters, Thomas Deselaers, Nicola Ferro, Julio Gonzalo
Place of PublicationBerlin
PublisherSpringer
Pages58-65
Number of pages8
ISBN (Print)978-3-642-04446-5
DOIs
Publication statusPublished - 2009
Event9th Workshop of the Cross-Language Evaluation Forum, CLEF 2008 - Aarhus, Denmark
Duration: 17 Sept 200819 Sept 2008
Conference number: 9

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume5706
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Workshop

Workshop9th Workshop of the Cross-Language Evaluation Forum, CLEF 2008
Abbreviated titleCLEF
Country/TerritoryDenmark
CityAarhus
Period17/09/0819/09/08

Keywords

  • Cross-lingual information retrieval
  • Query translation
  • Word sense disambiguation
  • Wikipedia
  • Comparable corpus

Fingerprint

Dive into the research topics of 'WikiTranslate: Query Translation for Cross-lingual Information Retrieval using only Wikipedia'. Together they form a unique fingerprint.

Cite this