Learning class-to-class selectional preferences

TL;DR

This paper introduces a novel model for learning class-to-class selectional preferences, capturing verb sense distinctions and shared preferences, and evaluates it on a word sense disambiguation task using syntactic relations.

Contribution

It extends existing models to class-to-class preferences, enabling better handling of verb senses and shared preferences among verb classes.

Findings

Model successfully captures sense-specific preferences.

Improves word sense disambiguation accuracy.

Demonstrates effectiveness on a small sense-disambiguated corpus.

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 papers extends previous statistical models to class-to-class preferences, and presents a model that learns selectional preferences for classes of verbs. The motivation is twofold: different senses of a verb may have different preferences, and some classes of verbs can share preferences. The model is tested on a word sense disambiguation task which uses subject-verb and object-verb relationships extracted from a small sense-disambiguated corpus.