A comprehensive review of Bengali word sense disambiguation

The entities of communication have an enormous impact on interaction. Textual data is an important attribute of communication. Textual analysis of this data is carried out by the linguistic researchers in various perspectives. It helps to understand the people’s perception by analyzing the contextual data into its various senses. The sense of a polysemous word is varied according to its context. Hence, the process of identifying the proper meaning of a polysemous word with respect to the context is known as word sense disambiguation (WSD). For the extraction of actual meaning, WSD is an essential technique in Natural Language Processing. Over the last two decades, a lot of algorithms have been proposed to solve this linguistic ambiguity problem in various languages. In addition, a number of review papers have been published in various most spoken languages. Even so, it is elevating that there is a discontinuity in the literature when it comes to the techniques of Bengali WSD. This paper confers an extensive survey work regarding approaches of Bengali WSD. It also presents a survey work of the existing dataset of Bengali WSD.