Measuring Thematic Fit with Distributional Feature Overlap

TL;DR

This paper presents a novel distributional approach for modeling predicate-argument thematic fit by using syntax-based DSMs to create role prototypes and measuring feature overlap, outperforming existing unsupervised methods.

Contribution

The paper introduces a new distributional method that constructs explicit verb-specific role prototypes and measures thematic fit through feature overlap, improving performance over prior systems.

Findings

Outperforms a baseline re-implementing a state-of-the-art system

Achieves better or comparable results to existing unsupervised systems

Provides explicit feature-based representations of semantic roles

Abstract

In this paper, we introduce a new distributional method for modeling predicate-argument thematic fit judgments. We use a syntax-based DSM to build a prototypical representation of verb-specific roles: for every verb, we extract the most salient second order contexts for each of its roles (i.e. the most salient dimensions of typical role fillers), and then we compute thematic fit as a weighted overlap between the top features of candidate fillers and role prototypes. Our experiments show that our method consistently outperforms a baseline re-implementing a state-of-the-art system, and achieves better or comparable results to those reported in the literature for the other unsupervised systems. Moreover, it provides an explicit representation of the features characterizing verb-specific semantic roles.