Graph Based Algorithms for Word Sense Induction and Disambiguation

This paper presents a survey of graph based methods for word sense induction and disambiguation. Many areas of Natural Language Processing like Word Sense Disambiguation (WSD), text summarization, keyword extraction make use of Graph based methods. The very idea behind graph based approach is to formulate the problems in graph setting and apply clustering to obtain a set of clusters (senses). The basic aim of this paper is to study various aspects of such graph based approaches in disambiguation of words. The paper also provides an insight into the results obtained by these techniques on standardized evaluation systems. Keywords-word sense disambiguation; graph-based;word sense induction; unsupervised methods;