Abstract
This paper describes the official runs of the Twenty-One group for TREC-7. The Twenty-One group participated in the ad-hoc and the cross-language track and made the following accomplishments: We developed a new weighting algorithm, which outperforms the popular Cornell version of BM25 on the ad-hoc collection. For the CLIR task we developed a fuzzy matching algorithm to recover from missing translations and spelling variants of proper names. Also for CLIR we investigated translation strategies that make extensive use of information from our dictionaries by identifying preferred translations, main translations and synonym translations, by defining weights of possible translations and by experimenting with probabilistic boolean matching strategies.
Original language | Undefined |
---|---|
Title of host publication | Proceedings of the seventh Text Retrieval Conference (TREC) |
Editors | E.M Voorhees, D.K. Harman |
Place of Publication | Gaithersburg, USA |
Publisher | National Institute of Standards and Technology |
Pages | 227-238 |
Number of pages | 12 |
Publication status | Published - 1999 |
Event | Seventh Text REtrieval Conference, TREC-7 1998 - Gaithersburg, United States Duration: 9 Nov 1999 → 11 Nov 1999 Conference number: 7 |
Publication series
Name | NIST Special Publications |
---|---|
Publisher | US National Institute of Standards and Technology |
Volume | 500-242 |
Conference
Conference | Seventh Text REtrieval Conference, TREC-7 1998 |
---|---|
Abbreviated title | TREC |
Country/Territory | United States |
City | Gaithersburg |
Period | 9/11/99 → 11/11/99 |
Keywords
- CR-H.3.3
- IR-66980
- EWI-9421
- METIS-119693