TESTING THE MAXIMUM-ENTROPY PRINCIPLE FOR INFORMATION-RETRIEVAL

Authors
KANTOR PB LEE JJ
Citation
Pb. Kantor et Jj. Lee, TESTING THE MAXIMUM-ENTROPY PRINCIPLE FOR INFORMATION-RETRIEVAL, Journal of the American Society for Information Science, 49(6), 1998, pp. 557-566
Citations number
14
Categorie Soggetti
Information Science & Library Science","Computer Science Information Systems","Computer Science Information Systems
Journal title
Journal of the American Society for Information Science → ACNP
ISSN journal
00028231
Volume
49
Issue
6
Year of publication
1998
Pages
557 - 566
Database
ISI
SICI code
0002-8231(1998)49:6<557:TTMPFI>2.0.ZU;2-X
Abstract
A probabilistic information retrieval method using the Maximum Entropy Principle (MEP) was proposed by Cooper and Huizinga (1982). Several r efinements of the MEP for information retrieval have been proposed by Kantor and Lee (1986, 1991), but the MEP has not been evaluated in any large database. This article examines the MEP retrieval method using the TREC5 database. The MEP is evaluated by several tests and compared with a ''naive ordering method'' and ''lexicographic ordering method. '' The MEP does not provide any startling improvement, and it works re asonably well only in the case of a small number of keys and a relativ ely small collection.