Chinese dependency parsing with large scale automatically constructed case structures

Kun Yu*, Daisuke Kawahara, Sadao Kurohashi

*Corresponding author for this work

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

18 Citations (Scopus)

Abstract

This paper proposes an approach using large scale case structures, which are automatically constructed from both a small tagged corpus and a large raw corpus, to improve Chinese dependency parsing. The case structure proposed in this paper has two characteristics: (1) it relaxes the predicate of a case structure to be all types of words which behaves as a head; (2) it is not categorized by semantic roles but marked by the neighboring modifiers attached to a head. Experimental results based on Penn Chinese Tree-bank show the proposed approach achieved 87.26% on unlabeled attachment score, which significantly outperformed the baseline parser without using case structures.

Original languageEnglish
Title of host publicationColing 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages1049-1056
Number of pages8
ISBN (Print)9781905593446
DOIs
Publication statusPublished - 2008
Externally publishedYes
Event22nd International Conference on Computational Linguistics, Coling 2008 - Manchester, United Kingdom
Duration: 2008 Aug 182008 Aug 22

Publication series

NameColing 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference
Volume1

Conference

Conference22nd International Conference on Computational Linguistics, Coling 2008
Country/TerritoryUnited Kingdom
CityManchester
Period08/8/1808/8/22

ASJC Scopus subject areas

  • Language and Linguistics
  • Computational Theory and Mathematics
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'Chinese dependency parsing with large scale automatically constructed case structures'. Together they form a unique fingerprint.

Cite this