A memory based approach to word sense disambiguation in Bengali using k-NN method

Author

Pandit, Rajat ; Naskar, Sudip Kumar

Author_Institution

Dept. of Comput. Sci., West Bengal State Univ., Kolkata, India

fYear

2015

fDate

9-11 July 2015

Firstpage

383

Lastpage

386

Abstract

Word Sense Disambiguation (WSD) is an important and challenging task in the area of Natural Language Processing (NLP) where the task is to find the correct sense of an ambiguous word given its context. There have been very few attempts on WSD in Bengali or in Indian languages. The k-Nearest-Neighbor (k-NN) algorithm is a very well known and popular method for text classification. The k-NN algorithm determines the classification of a new sample from its k nearest neighbors. In this paper, we present how k-NN algorithm can be effectively applied to the task of WSD in Bengali. The k-NN algorithm achieved an accuracy of over 71% in a WSD task in Bengali reported in this paper.

Keywords

classification; natural language processing; text analysis; Bengali language; Indian language; NLP; WSD; k-NN algorithm; k-NN method; k-nearest-neighbor algorithm; memory based approach; natural language processing; text classification; word sense disambiguation; Classification algorithms; Computational linguistics; Context; Knowledge based systems; Measurement; Training; Training data; Overlap metric; Word sense disambiguation; classification; k-nearest neighbor; supervised learning;

fLanguage

English

Publisher

ieee

Conference_Titel

Recent Trends in Information Systems (ReTIS), 2015 IEEE 2nd International Conference on

Conference_Location

Kolkata

Type

conf

DOI

10.1109/ReTIS.2015.7232909

Filename

7232909