Since Web users' queries are often too short, an accurate and interactive speech interface is believed very helpful, especially for WAP-based Web search engines. To provide high accurate speech recognition and effective itneractive search, a rigid and live web thesaurus that contains users' search terms plus a set of relations between their associated terms is highly in demand. The purpose of this paper is itnended to present a log-based approach for live thesaurus construction. Based on the live thesaurus, certain kinds of users' information behaviors could be characterized and a more effective voice-based search engine could be developed.
展开▼