Knowledge Based Approaches to Query Expansion in Information Retrieval英文资料.pdf

Bodner, R. and Song, F. (1996) Knowledge-based approaches to query expansion in information retrieval. In McCalla, G. (Ed.), Advances in Artificial Intelligence (pp. 146-158). New York: Springer. Knowledge-Based Approaches to Query Expansion in Information Retrieval Richard C. Bodner and Fei Song Department of Computing Information Science University of Guelph Guelph, Ontario, Canada N1G 2W1 {rbodner, fsong}@snowhite.cis.uoguelph.ca Textual information is becoming increasingly available in electronic forms. Users need tools to sift through non-relevant information and retrieve only those pieces relevant to their needs. The traditional methods such as Boolean operators and key terms have somehow reached their limitations. An emerging trend is to combine the traditional information retrieval and artificial intelligence techniques. This paper explores the possibility of extending traditional information retrieval systems with knowledge-based approaches to automatically expand natural language queries. Two types of knowledge-bases, a domain-specific and a general world knowledge, are used in the expansion process. Experiments are also conducted using different search strategies and various combinations of the knowledge-bases. Our results show that an increase in retrieval performance can be obtained using certain knowledge-based approaches. 1 Introduction The abundance of information available to a user can be overwhelming. Users generally require tools to help them sift through large collections of information and retrieve only those items of interest. The field of inf