Word sense disambiguation of Thai language with unsupervised learning

Many approach strategies can be employed to resolve word sense ambiguity with a reasonable degree of accuracy. These strategies are: knowledge-based, corpus-based, and hybrid-based. This paper pays attention to the corpus-based strategy that employs an unsupervised learning method for disambiguation. We report our investigation of Latent Semantic Indexing (LSI), an unsupervised learning, to the task of Thai noun and verbal word sense disambiguation. We report experiments on two Thai polysemous words, namely (SIC)/hua4/ and (SIC)/kep1/ that are used as a representative of Thai nouns and verbs respectively. The results of these experiments demonstrate the effectiveness and indicate the potential of applying vector-based distributional information measures to semantic disambiguation. Our approach performs better than a baseline system, which picks the most frequent sense.