International Journal of Computer Theory and Engineering

Frequency: Quarterly
ISSN: 1793-8201 (Print), 2972-4511 (Online)
Publisher:IACSIT Press

OPEN ACCESS
4.0
CiteScore

IJCTE 2015 Vol.7(6): 428-433
doi: 10.7763/IJCTE.2015.V7.997

TH_WSD: Thai Word Sense Disambiguation Using Cross-Language Knowledge Sources Approach

J. L. Mitrpanont , P. Chongcharoen

  • Faculty of Information and Communication Technology, Mahidol University, Bangkok, Thailand.

Abstract

The ambiguity in Thai Word is still a significant issue in translating Thai language to English. This paper presents the TH_WSD, a framework for Thai word ambiguous resolution using cross-language knowledge sources of AsianWordNet (AWN) and PrincetonWordNet (PWN) for lexical and word sense explorers. A semi-automated Thai WSD approach for non-specific domain using four disambiguation techniques, word forms, and even window sizes is proposed. The disambiguation techniques include path, vector, vector_pair and lesk. The 250 context words from four target words group which are วัด (wat), หัว (hua), เก็บ (kep) and เกาะ (koh) from bi-text corpora of SEAlang and Concordance are studied. The experimental results show that using AWN with vector technique and PWN with path technique provides better accuracy. However, for Thai WSD included time consideration, the vector technique with AWN at five window size is suitable.

Keywords

  • Natural language processing
  • word sense disambiguation
  • Wordnet
  • cross-language
  • AseanWordNet
997-TD040

How to Cite

Copied

J. L. Mitrpanont and P. Chongcharoen, "TH_WSD: Thai Word Sense Disambiguation Using Cross-Language Knowledge Sources Approach," International Journal of Computer Theory and Engineering, vol. 7, no. 6, pp. 428-433, 2015. https://doi.org/10.7763/IJCTE.2015.V7.997

Copyright & License

Copyright © 2015 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).

Article Metrics in Dimensions

Menu