Using Type Information to Improve Entity Coreference Resolution

TL;DR

This paper introduces a novel neural coreference resolution model that incorporates external type information, leading to modest accuracy improvements across multiple datasets.

Contribution

It is the first to leverage external semantic type information in neural coreference models, enhancing mention representation and consistency checks.

Findings

Modest accuracy gains with gold and predicted types

Effective use of type information across different corpora

Improved mention representations and consistency checks

Abstract

Coreference resolution (CR) is an essential part of discourse analysis. Most recently, neural approaches have been proposed to improve over SOTA models from earlier paradigms. So far none of the published neural models leverage external semantic knowledge such as type information. This paper offers the first such model and evaluation, demonstrating modest gains in accuracy by introducing either gold standard or predicted types. In the proposed approach, type information serves both to (1) improve mention representation and (2) create a soft type consistency check between coreference candidate mentions. Our evaluation covers two different grain sizes of types over four different benchmark corpora.