Using Sense Clustering for the Disambiguation of Words

Authors:  Henry Anaya-Sánchez, Aurora Pons-Porrata, Rafael Berlanga-Llavori

Polibits, 40, pp. 23-28, 2009.

Abstract:   Clustering methods have been extensively used in the solution of many Information Processing tasks in order to capture unknown object categories. This paper presents an approach to Word Sense Disambiguation based on clustering. The underlying idea is that the clustering of word senses provides a useful way to discover semantically related senses. We evaluate our proposal regarding both fine- and coarse-grained disambiguation. Experimental results over Senseval-3 all-words, SemCor 2.0 and SemEval-2007 corpora are presented. Promising values of precision and recall are obtained.

Keywords: Word sense disambiguation; clustering

PDF: Using Sense Clustering for the Disambiguation of Words, Alternative link