Despite exponential accumulation of electronic texts in the Internet age, effective search and reuse is not available for most texts due to the lack of association among them. Terms and the semantic relationship between terms have great potential in organizing and sharing textual information. We develop an agent-based approach for discovering term relationship in texts collected from the Web. The goal of the paper is to investigate which of the five generic relationships in text, including synonym, hypernym, hyponym, holonym and meronym, can be effectively discovered with the proposed approach.
展开▼