Word Importance Discrimination using Context Information

Authors :: FRENCH NATIONAL INSTITUTE FOR RESEARCH IN COMPUTER SCIENCE AND CONTROL SOPHIA ANTIPOLIS- MEDITERRANEAN RESEARCH CENTER (FRANCE)
Nemirovsky, Danil
Dobrynin, Vladimir
FRENCH NATIONAL INSTITUTE FOR RESEARCH IN COMPUTER SCIENCE AND CONTROL SOPHIA ANTIPOLIS- MEDITERRANEAN RESEARCH CENTER (FRANCE)
Nemirovsky, Danil
Dobrynin, Vladimir
Source :: DTIC
Publication Year :: 2008
Abstract: Word importance discrimination is a task deserving attention when one treats a topic from TREC where a topic is quite long. The goal of the process is to estimate importance of words which carry any (additional) information about user information needs. In our experiments we estimated word importance using context information of a word.<br />Presented at the Text REtrieval Conference (TREC 2008) (17th) held in Gaithersburg, Maryland on 18-21 November 2008. Published in the Text REtrieval Conference Proceedings, p1-7, November 2008. Sponsored in part by DARPA and ARDA. The original document contains color images.

Tools