Contrastive Representation Learning for Cross-Document Coreference Resolution of Events and Entities

TL;DR

This paper introduces a contrastive learning approach for cross-document coreference resolution of entities and events, significantly reducing computational costs while achieving state-of-the-art results on benchmark datasets.

Contribution

The paper proposes a novel contrastive representation learning method that decreases inference-time computations from quadratic to linear, improving efficiency in coreference resolution.

Findings

Achieves state-of-the-art performance on ECB+ corpus

Reduces transformer computations from n^2 to n at inference

Competitive results on multiple coreference metrics

Abstract

Identifying related entities and events within and across documents is fundamental to natural language understanding. We present an approach to entity and event coreference resolution utilizing contrastive representation learning. Earlier state-of-the-art methods have formulated this problem as a binary classification problem and leveraged large transformers in a cross-encoder architecture to achieve their results. For large collections of documents and corresponding set of $n$ mentions, the necessity of performing $n^{2}$ transformer computations in these earlier approaches can be computationally intensive. We show that it is possible to reduce this burden by applying contrastive learning techniques that only require $n$ transformer computations at inference time. Our method achieves state-of-the-art results on a number of key metrics on the ECB+ corpus and is competitive on others.