Skip to main navigation Skip to search Skip to main content

Khmer POS Tagging Using Conditional Random Fields

  • Mahidol University

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

Abstract

The transformation-based approach with hybrid of rule-based and tri-gram have already been introduced for Khmer part-of-speech (POS) tagging. In this study, in order to further explore this topic, we present an alternative approach to Khmer POS tagging using Conditional Random Fields (CRFs). Since the features greatly affect the tagging accuracy, we investigate five groups of features and use them with the CRF model. First, we study different contextual information and use it as our baseline model. We then analyze the characteristics of Khmer and come up with three additional groups of language-related features including morphemes, word-shapes and name-entities. We also explore the use of lexicon as features to further improve the accuracy of our tagger. Our proposed approach has been evaluated on a corpus of 41,058 words and 27 POS tags. The comparative study has shown that our proposed approach produces a competitive accuracy compared to other Khmer POS tagging approaches.

Original languageEnglish
Title of host publicationComputational Linguistics - 15th International Conference of the Pacific Association for Computational Linguistics, PACLING 2017, Revised Selected Papers
EditorsWin Pa Pa, Kôiti Hasida
PublisherSpringer Verlag
Pages169-178
Number of pages10
ISBN (Print)9789811084379
DOIs
Publication statusPublished - 2018
Event15th International Conference of the Pacific Association for Computational Linguistics, PACLING 2017 - Yangon, Myanmar
Duration: 16 Aug 201718 Aug 2017

Publication series

NameCommunications in Computer and Information Science
Volume781
ISSN (Print)1865-0929

Conference

Conference15th International Conference of the Pacific Association for Computational Linguistics, PACLING 2017
Country/TerritoryMyanmar
CityYangon
Period16/08/1718/08/17

Keywords

  • Conditional Random Fields
  • Khmer
  • POS tagging
  • Part-of-speech tagging

Fingerprint

Dive into the research topics of 'Khmer POS Tagging Using Conditional Random Fields'. Together they form a unique fingerprint.

Cite this