Measuring Semantic Similarity between Named Entities by Searching the Web Directory

• Published in: Proceedings of the IEEE/WIC/ACM International Conference on Web Intelligence pp. 461 - 465
• Main Authors: Liu, Jiahui, Birnbaum, Larry
• Format: Conference Proceeding
• Language: English
• Published: Washington, DC, USA IEEE Computer Society 02.11.2007
• Series: ACM Conferences
• Subjects: Computing methodologies > Machine learning > Learning paradigms > Supervised learning > Supervised learning by classification; Computing methodologies > Machine learning > Learning paradigms > Unsupervised learning > Cluster analysis; Computing methodologies > Machine learning > Machine learning approaches > Classification and regression trees; Information systems > Information retrieval; Information systems > Information retrieval > Document representation > Thesauri; Information systems > Information retrieval > Evaluation of retrieval results; Information systems > World Wide Web > Web applications; Information systems > World Wide Web > Web services
• ISBN: 0769530265; 9780769530260
• DOI: 10.1109/WI.2007.75

The importance of named entities in information retrieval and knowledge management has recently brought interest in characterizing semantic relationships between entities. In this paper, we propose a method for measuring semantic similarity, an important type of semantic relationship, between entities. The method is based on Google Directory, a search interface to the Open Directory Project. Via the search engine, we can locate the web pages relevant to an entity and automatically create a profile of the entity according to the directory assignments of its web pages, which capture various features of the entity. Using their profiles, the semantic similarity between entities can be measured in different dimensions. We apply the semantic similarity measurement to two knowledge acquisition tasks: thesaurus construction of entities and fine grained categorization of entities. Our experiments demonstrate that the proposed method works effectively in these two tasks.