Automatically acquired lexical knowledge improves Japanese joint morphological and dependency analysis

Daisuke Kawahara, Yuta Hayashibe, Hajime Morita, Sadao Kurohashi

研究成果: Conference contribution

4 被引用数 (Scopus)

抄録

This paper presents a joint model for morphological and dependency analysis based on automatically acquired lexical knowledge. This model takes advantage of rich lexical knowledge to simultaneously resolve word segmentation, POS, and dependency ambiguities. In our experiments on Japanese, we show the effectiveness of our joint model over conventional pipeline models.

本文言語English
ホスト出版物のタイトルIWPT 2017 - 15th International Conference on Parsing Technologies, Proceedings
出版社Association for Computational Linguistics (ACL)
ページ1-10
ページ数10
ISBN(電子版)9781945626739
出版ステータスPublished - 2017
外部発表はい
イベント15th International Conference on Parsing Technologies, IWPT 2017 - Pisa, Italy
継続期間: 2017 9 202017 9 22

出版物シリーズ

名前IWPT 2017 - 15th International Conference on Parsing Technologies, Proceedings

Conference

Conference15th International Conference on Parsing Technologies, IWPT 2017
国/地域Italy
CityPisa
Period17/9/2017/9/22

ASJC Scopus subject areas

  • 人工知能
  • 人間とコンピュータの相互作用
  • 言語学および言語

フィンガープリント

「Automatically acquired lexical knowledge improves Japanese joint morphological and dependency 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