A Game-Theoretic Approach to Word Sense Disambiguation

Abstract

This paper presents a new model for word sense disambiguation formulated in terms of evolution- ary game theory, where each word to be disambiguated is represented as a node on a graph whose edges represent words relations and senses are represented as classes. The words simultaneously update their class membership preferences according to the senses that neighbouring words are likely to choose. We use distributional and syntactical information to weight the influence that each word has on the decisions of the others and semantic similarity information to measure the strength of compatibility among the senses. With this information we can formulate the word sense disambiguation problem as a constrain satisfaction problem and solve it using tools derived from game theory, maintaining the coherence of the text. The model is based on two ideas: similar words should be assigned to similar classes; and the meaning of a word does not depends on all the words in a text but just on some of them. The paper provides an in-depth motivation of the idea of modeling the word sense disambiguation problem in terms of game theory which is illustrated by an example. The conclusion presents an extensive analysis on the combination of similarity measure to use in the framework and a comparison with state-of-the-art systems. The results show that our new model performs well and can be applied to different tasks and in different scenarios.