High - Precision Search via Question Abstraction for Japanese Question Answering

• Item type: SIG Technical Reports(1)
• 公開日: 2004-09-17
• タイトル: High - Precision Search via Question Abstraction for Japanese Question Answering
• タイトル / 言語: en
• タイトル: High - Precision Search via Question Abstraction for Japanese Question Answering
• 言語: eng
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: Knowledge Media Laboratory Toshiba Corporate R&D Center
• 著者所属: Knowledge Media Laboratory Toshiba Corporate R&D Center
• 著者所属: Knowledge Media Laboratory Toshiba Corporate R&D Center
• 著者所属: Knowledge Media Laboratory Toshiba Corporate R&D Center
• 著者所属: Knowledge Media Laboratory Toshiba Corporate R&D Center
• 著者所属(英): en
• 著者所属(英): Knowledge Media Laboratory, Toshiba Corporate R&D Center
• 著者所属(英): en
• 著者所属(英): Knowledge Media Laboratory, Toshiba Corporate R&D Center
• 著者所属(英): en
• 著者所属(英): Knowledge Media Laboratory, Toshiba Corporate R&D Center
• 著者所属(英): en
• 著者所属(英): Knowledge Media Laboratory, Toshiba Corporate R&D Center
• 著者所属(英): en
• 著者所属(英): Knowledge Media Laboratory, Toshiba Corporate R&D Center
• 著者名: Tetsuya, SAKAI; Yoshimi, SAITO; Tomoharu, KOKUBU; Makoto, KOYAMA; Toshihiko, MANABE
• 著者名(英): Tetsuya, Sakai; Yoshimi, Saito; Tomoharu, Kokubu; Makoto, Koyama; Toshihiko, Manabe
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: This paper explores the use of Question Abstraction i.e. Named Entity Recognition for questions input by the user for reranking retrieved documents to enhance retrieval precision for Japanese Question Answering (QA). Question Abstraction may help improve precision because (a) As named entities are often phrases it may have effects that are similar to phrasal or proximity search; (b) As named entity recognition is context-sensitive the named entity tags may help disambiguate ambiguous terms and phrases. Our experiments using several Japanese ``exact answer'' QA test collections show that this approach significantly improves IR precision but that this improvement is not necessarily carried over to the overall QA performance. Additionally we conduct preliminary experiments on the use of Question Abstraction for Pseudo-Relevance Feedback using Japanese {?em IR} test collections and find positive (though not statistically significant) effects. Thus the Question Abstraction approach probably deserves further investigations.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: This paper explores the use of Question Abstraction, i.e., Named Entity Recognition for questions input by the user, for reranking retrieved documents to enhance retrieval precision for Japanese Question Answering (QA). Question Abstraction may help improve precision because (a) As named entities are often phrases, it may have effects that are similar to phrasal or proximity search; (b) As named entity recognition is context-sensitive, the named entity tags may help disambiguate ambiguous terms and phrases. Our experiments using several Japanese ``exact answer'' QA test collections show that this approach significantly improves IR precision, but that this improvement is not necessarily carried over to the overall QA performance. Additionally, we conduct preliminary experiments on the use of Question Abstraction for Pseudo-Relevance Feedback using Japanese {\em IR} test collections, and find positive (though not statistically significant) effects. Thus the Question Abstraction approach probably deserves further investigations.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AN10114171
• 書誌情報: 情報処理学会研究報告情報学基礎（FI）; 巻 2004, 号 93(2004-FI-076), p. 139-146, 発行日 2004-09-17
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会