複数文質問のタイプ同定  [in Japanese] Classification of Multiple-sentence Questions  [in Japanese]

Access this Article

Search this Article

Author(s)

    • 田村 晃裕 TAMURA AKIHIRO
    • 東京工業大学大学院総合理工学研究科 Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology
    • 奥村 学 OKUMURA MANABU
    • 東京工業大学精密工学研究所 Precision and Intelligence Laboratory, Tokyo Institute of Technology

Abstract

既存の質問応答システムは,複数文で構成される質問には答えられない.そこで,我々はそのような複数文質問にも対応できる質問応答システムの構築を目指す.その第1 段階として,複数文質問の質問タイプを同定する手法を提案する.具体的には,まず最初に,入力として与えられた複数文質問から質問タイプを決める際に最も重要な1 文を抽出する.そして,その抽出された1 文を用いて質問タイプを同定するという手法をとる.また,本論文では,質問タイプを同定する際に有効な情報となる名詞を特定するルールも提案する.複数文質問を含んだ実験データに対して,これらの情報と手法を用いて質問タイプを同定することで,F 値が8.8%,正解率が4.4%改善できた.Conventional QA systems cannot answer to the questions composed of two or more sentences. Therefore, we aim to construct a QA system that can answer such multiple-sentence questions. As the first stage, we propose a method for classifying multiple-sentence questions into question types. Specifically, we first extract the core sentence from a given question text. Then, we use the core sentence in question classification. We also propose a rule for extracting the effective noun in question classification. The result of experiments with the dataset including multiple-sentence questions shows that the proposed method improves F-measure by 8.8% and accuracy by 4.4%.

Conventional QA systems cannot answer to the questions composed of two or more sentences. Therefore, we aim to construct a QA system that can answer such multiple-sentence questions. As the first stage, we propose a method for classifying multiple-sentence questions into question types. Specifically, we first extract the core sentence from a given question text. Then, we use the core sentence in question classification. We also propose a rule for extracting the effective noun in question classification. The result of experiments with the dataset including multiple-sentence questions shows that the proposed method improves F-measure by 8.8% and accuracy by 4.4%.

Journal

  • IPSJ journal

    IPSJ journal 47(6), 1954-1962, 2006-06-15

    Information Processing Society of Japan (IPSJ)

References:  12

Codes

  • NII Article ID (NAID)
    110004729755
  • NII NACSIS-CAT ID (NCID)
    AN00116647
  • Text Lang
    JPN
  • Article Type
    Journal Article
  • ISSN
    1882-7764
  • NDL Article ID
    7993446
  • NDL Source Classification
    ZM13(科学技術--科学技術一般--データ処理・計算機)
  • NDL Call No.
    Z14-741
  • Data Source
    CJP  NDL  NII-ELS  IPSJ 
Page Top