トピック型ブーリアンクエリモデルおよび一般的なランキングモデルを用いた学術論文検索システムの構築

情報処理学会

この論文をさがす

抄録

In an academic paper search, it is important that the search returns comprehensive results that are relevant to the user's information need by creating a Boolean query. However, it is difficult to anticipate all possible terms that authors of relevant papers might have used. We propose a Boolean-based search method based on topic analysis using latent Dirichlet allocation. Our method considers synonyms and expressions similar to the search terms, which a user might not anticipate. The sets retrieved by our method and by general ranking method are different because the purpose of the ranking method is to high rank the relevant papers and our method is focused on comprehensively collecting relevant papers. Therefore, it is able to that more high performance search result could be obtained by combining both sets.

収録刊行物

キーワード

詳細情報 詳細情報について

問題の指摘

ページトップへ