Neural network-based model for Japanese predicate argument structure analysis

Tomohide Shibata, Daisuke Kawahara, Sadao Kurohashi

研究成果: Chapter in Book/Report/Conference proceedingConference 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.

本文言語英語
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
出版ステータス出版済み - 2016
イベント54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Berlin, ドイツ
継続期間: 8 7 20168 12 2016

出版物シリーズ

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

その他

その他54th Annual Meeting of the Association for Computational Linguistics, ACL 2016
Countryドイツ
CityBerlin
Period8/7/168/12/16

All Science Journal Classification (ASJC) codes

  • Language and Linguistics
  • Linguistics and Language

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