Overview - Cross-Language 2002

Proceedings | Results | Runs | Participants

Nine teams participated in the TREC-2002 cross-language information retrieval track, which focused on retrieving Arabic language documents based on 50 topics that were originally prepared in English. Arabic translations of the topic descriptions were also made available to facilitate monolingual Arabic runs. This was the second year in which a large Arabic document collection was available. Three new teams joined the evaluation, and the cross-language aspect of the evaluation received more attention this year than in TREC-2001. A set of standard linguistic resources was made available to facilitate cross-system comparisons, and their use as a contrastive condition was encouraged. Unique contributions to the relevance pools were more typical of previous TREC evaluations then the results of TREC-2001 had been for the same document collection, with no run uniquely contributing more than 6% of the known relevant documents.

Track coordinator(s):

• D.W. Oard, University of Maryland, College Park
• F.C. Gey, University of California, Berkeley

Tasks:

• arabic: Arabic
• english: English

---