Revisiting Selectional Preferences for Coreference Resolution

TL;DR

This paper introduces a dependency-based embedding model for selectional preferences that enhances coreference resolution performance, matching state-of-the-art results but with increased complexity and questionable cost-effectiveness.

Contribution

The paper presents a novel embedding model for selectional preferences that can be integrated into coreference resolvers to improve accuracy.

Findings

Improved coreference resolution performance on CoNLL dataset

Model matches state-of-the-art results of more complex systems

Increased complexity raises questions about practical value

Abstract

Selectional preferences have long been claimed to be essential for coreference resolution. However, they are mainly modeled only implicitly by current coreference resolvers. We propose a dependency-based embedding model of selectional preferences which allows fine-grained compatibility judgments with high coverage. We show that the incorporation of our model improves coreference resolution performance on the CoNLL dataset, matching the state-of-the-art results of a more complex system. However, it comes with a cost that makes it debatable how worthwhile such improvements are.