Word sense disambiguation is an important and challenging task in natural language processing. Its goal is to find the correct sense in which a word occurs in a sentence or a query when it can have multiple meanings. It is used in various applications of NLP like machine learning, text summarization, information retrieval etc. In this paper, we made a survey of supervised, unsupervised, knowledge based and corpus based approaches of word sense disambiguation. In this paper, study of various word sense disambiguation strategies has been done.