Mining Class Association Rules for Word Sense Disambiguation

In this paper we propose an approach to the task of Word Sense Disambiguation problem that uses Class Association Rules to create an effective and human-understandable rule-based classifier. We present the accuracy of classification of selected polysemous words on an evaluation corpus using the proposed method and compare it to other known approaches. We discuss the advantages and weaknesses of a classifier based on association rules and present ideas for future work on the idea.