A* CCG parsing with a supertag and dependency factored model

Masashi Yoshikawa, Hiroshi Noji, Yuji Matsumoto

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

23 Citations (Scopus)

Abstract

We propose a new A* CCG parsing model in which the probability of a tree is decomposed into factors of CCG categories and its syntactic dependencies both defined on bi-directional LSTMs. Our factored model allows the precomputation of all probabilities and runs very efficiently, while modeling sentence structures explicitly via dependencies. Our model achieves the state-of-the-art results on English and Japanese CCG parsing.

Original languageEnglish
Title of host publicationACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
PublisherAssociation for Computational Linguistics (ACL)
Pages277-287
Number of pages11
ISBN (Electronic)9781945626753
DOIs
Publication statusPublished - 2017
Externally publishedYes
Event55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 - Vancouver, Canada
Duration: 2017 Jul 302017 Aug 4

Publication series

NameACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
Volume1

Other

Other55th Annual Meeting of the Association for Computational Linguistics, ACL 2017
Country/TerritoryCanada
CityVancouver
Period17/7/3017/8/4

ASJC Scopus subject areas

  • Language and Linguistics
  • Artificial Intelligence
  • Software
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'A* CCG parsing with a supertag and dependency factored model'. Together they form a unique fingerprint.

Cite this