Header menu link for other important links
Intelligent encoding of concepts in Web document retrieval
J. Zakos, B. Verma, X. Li,
Published in Institute of Electrical and Electronics Engineers Inc.
Pages: 72 - 77
The main aim of the proposed approach presented in this paper is to improve Web information retrieval effectiveness by overcoming the problems associated with a typical keyword matching retrieval system, through the use of concepts and an intelligent fusion of confidence values. By exploiting the conceptual hierarchy of the WordNet (G. Miller, 1995) knowledge base, we show how to effectively encode the conceptual information in a document using the semantic information implied by the words that appear within it. Rather than treating a word as a string made up of a sequence of characters, we consider a word to represent a concept. © 2003 IEEE.