Complement keywords for query toward efficient information retrieval

Proposes a method to complement the keywords for queries based on the hidden or implicit correlation between the keywords specified by the user, for efficient information retrieval. In accordance with the rapid development of the Internet and the World Wide Web, it has been getting harder and harder to pinpoint desired and necessary documents from among this huge information resource. Various search engines have been developed to search for candidates for the required information based on keywords specified by the user. However, it is hard for the user to specify the keywords completely enough to retrieve the necessary documents. Since there often exists some semantic correlation between the specified keywords, this paper proposes to complement an incomplete set of keywords by utilizing the semantic correlation as another keyword to narrow the scope of the search. Experiments were carried out to investigate the effectiveness of the proposed method, and the result hinted at the effectiveness of our approach as a pre-processing technique to narrow the scope of the search for search engines.