In Statistical Machine Translation (SMT), there are many source words that can present different translations or senses. Word Sense Disambiguation (WSD) system is designed to determine which one of the senses of an ambiguous word is invoked in a particular context around the word. 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. This paper presents a new WSD method for ambiguous Myanmar words. It is based on supervised learning approach, Nearest Neighbor Cosine Classifier. The system uses Myanmar-English Parallel Corpus as a training resource. As an advantage, the system can overcome the problem of translation ambiguity from Myanmar to English language translation.