比喩を含む言語表現の理解 : 形容詞・名詞句と隠喩

書誌事項

タイトル別名
  • Understanding Figurative Language : Adjective Noun Combination and Metaphor

この論文をさがす

抄録

<p>Metaphorical or figurative expressions are easily found in our daily life. Studying how to understand figurative language is necessary for the development of both cognitive science and natural language processing. This paper presents a method for understanding figurative adjective-noun combinations by using the primitive-based representation of adjectives described in our previous paper. Understanding adjective-noun phrases can be modeled as applying the adjective meaning to refine an attribute value in the prototype-represented target noun concept. Our method can interpret both literal and figurative phrases without the need for advance discrimination. Our method consists of three parts. The first part is a disambiguation algorithm for choosing among an adjective's senses. This algorithm calculates the probability for each sense of an adjective by using Dempster-Shafer Theory. If these calculated probabilities pass two criterion for ambiguity and vagueness, the phrase is determined to be literal. The second part is the interpretation of figurative adjective meaning. This can be done by two methods, one is by means of the primitive relations described in our previous paper, and the other is by topological primitive matching. Topological primitive matching is the method to select candidate primitives. Each attribute has its own two-dimensional space. All primitives are placed at the point in the space of attributes to which it corresponds. This topological representation is psychologically plausible. The third is an attribute-value mapping algorithm. This algorithm decides which attribute value to mapped when two or more candidates have same attribute. This part also handles the processing of connotative meaning. Moreover, we show that "A is (like) B" metaphors can be interpreted using the same method.</p>

収録刊行物

  • 人工知能

    人工知能 8 (2), 201-211, 1993-03-01

    一般社団法人 人工知能学会

被引用文献 (8)*注記

もっと見る

参考文献 (19)*注記

もっと見る

詳細情報 詳細情報について

  • CRID
    1390004222628791296
  • NII論文ID
    110002807653
  • NII書誌ID
    AN10067140
  • DOI
    10.11517/jjsai.8.2_201
  • ISSN
    24358614
    21882266
  • 本文言語コード
    ja
  • データソース種別
    • JaLC
    • CiNii Articles
  • 抄録ライセンスフラグ
    使用不可

問題の指摘

ページトップへ