Integrating selectional preferences in WordNet

TL;DR

This paper introduces a novel model for learning and integrating class-to-class selectional preferences into WordNet, enhancing semantic understanding and disambiguation by leveraging untagged corpora and sense inheritance.

Contribution

It extends existing models to class-to-class preferences, providing an algorithm for integration into WordNet and demonstrating practical benefits for word sense disambiguation.

Findings

Successful learning of class-to-class preferences from untagged corpora

Effective integration of preferences into WordNet structure

Improved performance on word sense disambiguation tasks

Abstract

Selectional preference learning methods have usually focused on word-to-class relations, e.g., a verb selects as its subject a given nominal class. This paper extends previous statistical models to class-to-class preferences, and presents a model that learns selectional preferences for classes of verbs, together with an algorithm to integrate the learned preferences in WordNet. The theoretical motivation is twofold: different senses of a verb may have different preferences, and classes of verbs may share preferences. On the practical side, class-to-class selectional preferences can be learned from untagged corpora (the same as word-to-class), they provide selectional preferences for less frequent word senses via inheritance, and more important, they allow for easy integration in WordNet. The model is trained on subject-verb and object-verb relationships extracted from a small corpus disambiguated with WordNet senses. Examples are provided illustrating that the theoretical motivations are well founded, and showing that the approach is feasible. Experimental results on a word sense disambiguation task are also provided.