Neural joint model for transition-based Chinese syntactic analysis

Shuhei Kurita, Daisuke Kawahara, Sadao Kurohashi

研究成果: Conference contribution

27 被引用数 (Scopus)

抄録

We present neural network-based joint models for Chinese word segmentation, POS tagging and dependency parsing. Our models are the first neural approaches for fully joint Chinese analysis that is known to prevent the error propagation problem of pipeline models. Although word embeddings play a key role in dependency parsing, they cannot be applied directly to the joint task in the previous work. To address this problem, we propose embeddings of character strings, in addition to words. Experiments show that our models outperform existing systems in Chinese word segmentation and POS tagging, and perform preferable accuracies in dependency parsing. We also explore bi-LSTM models with fewer features.

本文言語English
ホスト出版物のタイトルACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
出版社Association for Computational Linguistics (ACL)
ページ1204-1214
ページ数11
ISBN(電子版)9781945626753
DOI
出版ステータスPublished - 2017
外部発表はい
イベント55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 - Vancouver, Canada
継続期間: 2017 7月 302017 8月 4

出版物シリーズ

名前ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
1

Other

Other55th Annual Meeting of the Association for Computational Linguistics, ACL 2017
国/地域Canada
CityVancouver
Period17/7/3017/8/4

ASJC Scopus subject areas

  • 言語および言語学
  • 人工知能
  • ソフトウェア
  • 言語学および言語

フィンガープリント

「Neural joint model for transition-based Chinese syntactic 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