Skip to main navigation Skip to search Skip to main content

Conversion between dependency structures and phrase structures using a head finder algorithm

  • Xinxin Li*
  • , Xuan Wang
  • , Lin Yao
  • *Corresponding author for this work
  • Harbin Institute of Technology Shenzhen

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

Abstract

This paper proposes how to convert projective dependency structures into flat phrase structures with language-independent syntactic categories, and use a head finder algorithm to convert these phrase structures back into dependency structures. The head finder algorithm is implemented by a maximum entropy approach with constraint information. The converted phrase structures can be parsed using a hierarchical coarse-to-fine method with latent variables. Experimental results show that the approach finds 98.8% heads of all phrases, and our algorithm achieves state-of-the-art dependency parsing performance in English Treebank.

Original languageEnglish
Title of host publicationProceedings of the 6th International Conference on Natural Language Processing and Knowledge Engineering, NLP-KE, 2010
DOIs
StatePublished - 2010
Externally publishedYes
Event6th International Conference on Natural Language Processing and Knowledge Engineering, NLP-KE 2010 - Beijing, China
Duration: 21 Aug 201023 Aug 2010

Publication series

NameProceedings of the 6th International Conference on Natural Language Processing and Knowledge Engineering, NLP-KE 2010

Conference

Conference6th International Conference on Natural Language Processing and Knowledge Engineering, NLP-KE 2010
Country/TerritoryChina
CityBeijing
Period21/08/1023/08/10

Keywords

  • Dependency structures
  • Latent variables
  • Maximum entropy
  • Phrase structures

Fingerprint

Dive into the research topics of 'Conversion between dependency structures and phrase structures using a head finder algorithm'. Together they form a unique fingerprint.

Cite this