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.
Index Terms—Natural language processing, word sense
disambiguation, Wordnet, cross-language, AseanWordNet.
The authors are with the Faculty of Information and Communication
Technology, Mahidol University, Bangkok, Thailand (e-mail:
jarernsri.mit@mahidol.ac.th, premchai@bangkok.go.th).
[PDF]
Cite: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.