Skip to main navigation Skip to search Skip to main content

A comparison of chinese parsers for stanford dependencies

  • School of Computer Science and Technology, Harbin Institute of Technology
  • Stanford University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Stanford dependencies are widely used in natural language processing as a semanticallyoriented representation, commonly generated either by (i) converting the output of a constituent parser, or (ii) predicting dependencies directly. Previous comparisons of the two approaches for English suggest that starting from constituents yields higher accuracies. In this paper, we re-evaluate both methods for Chinese, using more accurate dependency parsers than in previous work. Our comparison of performance and efficiency across seven popular open source parsers (four constituent and three dependency) shows, by contrast, that recent higher-order graph-based techniques can be more accurate, though somewhat slower, than constituent parsers. We demonstrate also that n-way jackknifing is a useful technique for producing automatic (rather than gold) partof- speech tags to train Chinese dependency parsers. Finally, we analyze the relations produced by both kinds of parsing and suggest which specific parsers to use in practice.

Original languageEnglish
Title of host publication50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference
Pages11-16
Number of pages6
StatePublished - 2012
Externally publishedYes
Event50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Jeju Island, Korea, Republic of
Duration: 8 Jul 201214 Jul 2012

Publication series

Name50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference
Volume2

Conference

Conference50th Annual Meeting of the Association for Computational Linguistics, ACL 2012
Country/TerritoryKorea, Republic of
CityJeju Island
Period8/07/1214/07/12

Fingerprint

Dive into the research topics of 'A comparison of chinese parsers for stanford dependencies'. Together they form a unique fingerprint.

Cite this