Neural network-based model for Japanese predicate argument structure analysis

Tomohide Shibata, Daisuke Kawahara, Sadao Kurohashi

研究成果: Conference contribution

9 被引用数 (Scopus)

抄録

This paper presents a novel model for Japanese predicate argument structure (PAS) analysis based on a neural network framework. Japanese PAS analysis is challenging due to the tangled characteristics of the Japanese language, such as case disappearance and argument omission. To unravel this problem, we learn selectional preferences from a large raw corpus, and incorporate them into a SOTA PAS analysis model, which considers the consistency of all PAS s in a given sentence. We demonstrate that the proposed PAS analysis model significantly outperforms the base SOTA system.

本文言語English
ホスト出版物のタイトル54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers
出版社Association for Computational Linguistics (ACL)
ページ1235-1244
ページ数10
ISBN(電子版)9781510827585
DOI
出版ステータスPublished - 2016
外部発表はい
イベント54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Berlin, Germany
継続期間: 2016 8 72016 8 12

出版物シリーズ

名前54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers
3

Conference

Conference54th Annual Meeting of the Association for Computational Linguistics, ACL 2016
国/地域Germany
CityBerlin
Period16/8/716/8/12

ASJC Scopus subject areas

  • 言語および言語学
  • 言語学および言語

フィンガープリント

「Neural network-based model for Japanese predicate argument structure analysis」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル