Using text corpora for understanding polysemy in Bangla

Polysemy implies the presence of more than one sense of a particular word both in its context-bound and context-free situation. The inherent aspect of polysemy is that a particular word will show multiple sense variations related by way of semantic extension and conceptual expansion. In the last fifty years or so, polysemy has been recognised as one of the central issues in lexical semantics, word sense disambiguation (WSD), actual sense extraction (ASE), language learning, conceptual categorisation of words as well as in computer processing of language. Language users can identify a polysemous word quite easily, but are not equipped to decipher all its possible sense variations without appropriate reference to a proper knowledge-base and other relevant information embedded within contextual environments. We make an empirical effort to understand the basic nature of polysemy in Bangla. We also intend to know how words denote sense variations, which factors are instrumental in making them polysemous, what impact they have on language understanding, and how sense variation can be best understood using information from various sources of knowledge bases. Finally, we use a method to understand the role of various contexts, obtained from corpora, in maintaining an interface between words and their sense variations. Quick reference to local context is handy at times, but reference to focal, topical and global contexts as well as an extralinguistic knowledge base is necessary for understanding sense variation and obtaining actual contextual sense.