Overview of the Sixth Text REtrieval Conference (TREC-6)

Citation
Em. Voorhees et D. Harman, Overview of the Sixth Text REtrieval Conference (TREC-6), INF PR MAN, 36(1), 2000, pp. 3-35
Citations number
33
Categorie Soggetti
Library & Information Science","Information Tecnology & Communication Systems
Journal title
INFORMATION PROCESSING & MANAGEMENT
ISSN journal
03064573 → ACNP
Volume
36
Issue
1
Year of publication
2000
Pages
3 - 35
Database
ISI
SICI code
0306-4573(200001)36:1<3:OOTSTR>2.0.ZU;2-O
Abstract
The Text REtrieval Conference is a workshop series designed to encourage re search on text retrieval for realistic applications by providing large test collections, uniform scoring procedures and a forum for organizations inte rested in comparing results. TREC contains two main retrieval tasks plus op tional subtasks that allow participants to focus on particular common subpr oblems in retrieval. The emphasis on individual experiments evaluated in a common setting has proven to be very successful. In the six years since the beginning of TREC, the state of the art in retrieval effectiveness has app roximately doubled, and technology transfer among research labs and between research systems and commercial products has accelerated. In addition, TRE C has sponsored the first large-scale evaluations of Chinese language retri eval, retrieval of speech and retrieval across different languages. Publish ed by Elsevier Science Ltd.