Automatically acquired lexical knowledge improves Japanese joint morphological and dependency analysis

Daisuke Kawahara, Yuta Hayashibe, Hajime Morita, Sadao Kurohashi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

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.

Original languageEnglish
Title of host publicationIWPT 2017 - 15th International Conference on Parsing Technologies, Proceedings
PublisherAssociation for Computational Linguistics (ACL)
Pages1-10
Number of pages10
ISBN (Electronic)9781945626739
Publication statusPublished - 2017
Externally publishedYes
Event15th International Conference on Parsing Technologies, IWPT 2017 - Pisa, Italy
Duration: 2017 Sep 202017 Sep 22

Publication series

NameIWPT 2017 - 15th International Conference on Parsing Technologies, Proceedings

Conference

Conference15th International Conference on Parsing Technologies, IWPT 2017
Country/TerritoryItaly
CityPisa
Period17/9/2017/9/22

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'Automatically acquired lexical knowledge improves Japanese joint morphological and dependency analysis'. Together they form a unique fingerprint.

Cite this