An Associative Information Retrieval Based on the Dependency of Term Co-occurrence

This paper proposes a method to lead users to appropriate information based on associative information access. People of nowadays can access Web resources easily. However it is difficult to reach the information that satisfies users' requests. The results obtained from search engines usually contain large amount of unnecessary information. Our target users are the persons who could not express appropriate keywords for information retrieval. To support such users, we clarified the several requirements of an associative information access support system. According to these requirements, we propose Word Colony that visualizes the overview of the contents of results and suggests unexpected words as new keywords for the next retrieval. To design Word Colony, we introduced the notion of the dependency of term co-occurrence (DTC) in a document. In this paper, we describe the details of DTC, Word Colony and its demonstration.

[1]  Yukio Ohsawa,et al.  KeyGraph: automatic indexing by co-occurrence graph based on building construction metaphor , 1998, Proceedings IEEE International Forum on Research and Technology Advances in Digital Libraries -ADL'98-.

[2]  Makoto Iwayama,et al.  Associative information access using DualNAVI , 2000, Proceedings 2000 Kyoto International Conference on Digital Libraries: Research and Practice.

[3]  Akihiko Takano,et al.  Association Computation for Information Access , 2002, APLAS.

[4]  Makoto Iwayama,et al.  Information Access Based on Associative Calculation , 2000, SOFSEM.