文書内に現れる因果関係の出現特性調査  [in Japanese] Characteristics of In-text Causal Relations  [in Japanese]

Access this Article

Search this Article

Author(s)

    • 乾 孝司 INUI Takashi
    • 東京工業大学精密工学研究所 Precision and Intelligence Laboratory, 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

本稿では,文書内に現れる因果関係の出現特性を調査した結果について述べる.まず,因果関係情報を一定量の文書集合に対して付与し,因果関係タグ付きコーパスを作成する.その後,コーパスに付与された情報を元に,文書内での因果関係の出現傾向を定量的に調査する.因果関係は定義すること自体が困難な概念であり,従来,因果関係の有無の判断には,人間の主観に頼らざるをえなかった.本研究では,因果関係情報を付与する際,言語テンプレートに基づく判断基準を採用し,得られる因果関係情報からタグ付け作業者の主観をできる限り排除することを試みる.出現特性の調査項目として,(i)手がかり標識の有無,(ii)出来事表現の統語カテゴリ,(iii)出来事表現の文内位置,の3つの観点を取り上げ,因果関係が多様な言語表現形態で,かつ,多様な位置に現れることを示す.In this paper, we report the results of our investigation of the characteristics of in-text causal relations. First, we designed causal relation tags. With our designed tag set, annotators annotated a set of Japanese text documents. Then, using the annotated corpus, we investigated the causal relation instances from three viewpoints: (i) cue phrase markers, (ii) part-of-speech information, and (iii) position in sentences. Our quantitative study shows that what amount of causal relation instances are present, where these relation instances are present, and which types of linguistic expressions are used for expressing these relation instances in text.

In this paper, we report the results of our investigation of the characteristics of in-text causal relations. First, we designed causal relation tags. With our designed tag set, annotators annotated a set of Japanese text documents. Then, using the annotated corpus, we investigated the causal relation instances from three viewpoints: (i) cue phrase markers, (ii) part-of-speech information, and (iii) position in sentences. Our quantitative study shows that what amount of causal relation instances are present, where these relation instances are present, and which types of linguistic expressions are used for expressing these relation instances in text.

Journal

  • IPSJ SIG Notes

    IPSJ SIG Notes 2005(50(2005-SLP-056)), 81-88, 2005-05-27

    Information Processing Society of Japan (IPSJ)

Cited by:  1

Codes

  • NII Article ID (NAID)
    110002950661
  • NII NACSIS-CAT ID (NCID)
    AN10442647
  • Text Lang
    JPN
  • Article Type
    Journal Article
  • ISSN
    09196072
  • NDL Article ID
    7380384
  • 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.
    Z14-1121
  • Data Source
    CJPref  NDL  NII-ELS  IPSJ 
Page Top