Skip to main navigation Skip to search Skip to main content

Chinese chunking based on coarse-grained part-of-speech features

  • Guang Lu Sun*
  • , Yibo Xue
  • , Zhiming Xu
  • , Fei Lang
  • *Corresponding author for this work
  • Tsinghua University
  • Harbin University of Science and Technology
  • School of Computer Science and Technology, Harbin Institute of Technology

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

Abstract

Although part-of-speech (POS) is an effective feature for Chinese Chunking, the POS-tagging errors generated by automatic POS tagger leads to almost 10% performance drop in F-score. To solve this problem, this paper presents new features to replace the POS features, namely the coarse-grained part-of-speech features. Combining with the methods of processing out-of-vocabulary words, the new features are utilized in the Chinese chunking model. Experimental results show that the new features can contribute 2.71% performance improvement over the baseline method.

Original languageEnglish
Title of host publication2009 International Conference on Asian Language Processing
Subtitle of host publicationRecent Advances in Asian Language Processing, IALP 2009
Pages226-229
Number of pages4
DOIs
StatePublished - 2009
Externally publishedYes
Event2009 International Conference on Asian Language Processing: Recent Advances in Asian Language Processing, IALP 2009 - Singapore, Singapore
Duration: 7 Dec 20099 Dec 2009

Publication series

Name2009 International Conference on Asian Language Processing: Recent Advances in Asian Language Processing, IALP 2009

Conference

Conference2009 International Conference on Asian Language Processing: Recent Advances in Asian Language Processing, IALP 2009
Country/TerritorySingapore
CitySingapore
Period7/12/099/12/09

Keywords

  • Chunking
  • Coarse-grained features
  • Part-of-speech
  • Propagated errors

Fingerprint

Dive into the research topics of 'Chinese chunking based on coarse-grained part-of-speech features'. Together they form a unique fingerprint.

Cite this