A Supervised Approach on Gurmukhi Word Sense Disambiguation Using K-NN Method
Himdweep Walia, Ajay Rana, Vineet Kansal · 2018
The primary objective of Natural Language Processing (NLP) is to ensure that communication is established between the human and the machine. An ambiguous word is the one which has more than one meaning. The purpose of Word Sense Disambiguation (WSD), an important area of NLP, is to ensure that the machine is able to correctly find the context in which the word is being used. A number of different supervised, semi-supervised and un-supervised algorithms are being employed to carr y out the same. One such supervised approach is k-NN algorithm which we have implemented in disambiguating words in Gurmukhi. Gurmukhi (or popularly known as Punjabi) is the 17th most spoken language in the world. For this paper we have used the Punjabi Corpora (obtained from Evaluations and Language Resources Distribution Agency, Paris, France) which has been sense-tagged with 100 words.