Automatic Recognition of Verbal Polysemy

スポンサーリンク

概要

• 論文の詳細を見る

• Polysemy causes difficulties with the semantic clustering of words in corpus-based linguistics, and also leads to the problem of word-sense ambiguity in NLP systems. In this paper, we give a definition of polysemy from the viewpoint of clustering and propose an overlapping clustering algorithm which recognises verbal polysemies in a textual corpus. The main characteristic of our algorithm is that it explicitly introduces new entities called hypothetical verbs when an entity is judged polysemous, and associates them with the context of the original entity. We have conducted experiments in order to examine the effects of our algorithm, and the results demonstrate the effectiveness of the method.

• 一般社団法人情報処理学会の論文
• 1996-08-15

著者

• Tsujii J

  Univ. Tokyo

• FUKUMOTO FUMIYO

  Department of Electrical Engineering and Computer Science, Faculty of Engineering, Yamanashi Univers

• Fukumoto Fumiyo

  Department Of Electrical Engineering And Computer Science Faculty Of Engineering Yamanashi Universit

• Tsujii Jun′ichi

  Department of Information Science, Faculty of Science, University of Tokyo

関連論文

• Automatic Recognition of Verbal Polysemy

スポンサーリンク