Word sense disambiguation system for Myanmar word in support of Myanmar-English machine translation

Word Sense Disambiguation (WSD) has always been a key problem in Natural Language Processing. WSD is defined as the task of finding the correct sense of a word in a specific context. It is an intermediate task essential to many natural language processing problems, including machine translation, information retrieval and speech processing. There is not any cited work for resolving ambiguity of words in Myanmar language. In this paper, we propose an approach to solve the ambiguity of Myanmar words for Myanmar-English machine translation. Our approach is based on Nearest Neighbor Cosine classifier to disambiguate ambiguous words with part-of-speech `noun' and `verb', which uses topical feature that represent co-occurring words in bag-of-word feature. The system uses Myanmar-English parallel corpus as training data. The proposed system can improve the translation accuracy for Myanmar-English machine translation system.