Triad-based Neural Network for Coreference Resolution

TL;DR

This paper introduces a triad-based neural network for coreference resolution that models mutual dependencies among three mentions simultaneously, achieving state-of-the-art results without relying heavily on handcrafted features.

Contribution

It presents the first neural network system to model mutual dependencies among more than two mentions at the mention level, improving coreference resolution accuracy.

Findings

Achieved state-of-the-art results on CoNLL 2012 dataset

The model does not rely on many handcrafted features

Triads can be extended to higher-order polyads

Abstract

We propose a triad-based neural network system that generates affinity scores between entity mentions for coreference resolution. The system simultaneously accepts three mentions as input, taking mutual dependency and logical constraints of all three mentions into account, and thus makes more accurate predictions than the traditional pairwise approach. Depending on system choices, the affinity scores can be further used in clustering or mention ranking. Our experiments show that a standard hierarchical clustering using the scores produces state-of-art results with gold mentions on the English portion of CoNLL 2012 Shared Task. The model does not rely on many handcrafted features and is easy to train and use. The triads can also be easily extended to polyads of higher orders. To our knowledge, this is the first neural network system to model mutual dependency of more than two members at mention level.