Coreference Resolution as Query-based Span Prediction

TL;DR

This paper introduces a novel query-based span prediction method for coreference resolution, leveraging machine reading comprehension techniques to improve accuracy and generalization, achieving state-of-the-art results on key benchmarks.

Contribution

It formulates coreference resolution as a span prediction task within an MRC framework, enabling flexible mention retrieval and effective use of existing datasets for data augmentation.

Findings

Achieved 87.5 F1 on GAP benchmark

Achieved 83.1 F1 on CoNLL-2012 benchmark

Significant performance improvements over previous models

Abstract

In this paper, we present an accurate and extensible approach for the coreference resolution task. We formulate the problem as a span prediction task, like in machine reading comprehension (MRC): A query is generated for each candidate mention using its surrounding context, and a span prediction module is employed to extract the text spans of the coreferences within the document using the generated query. This formulation comes with the following key advantages: (1) The span prediction strategy provides the flexibility of retrieving mentions left out at the mention proposal stage; (2) In the MRC framework, encoding the mention and its context explicitly in a query makes it possible to have a deep and thorough examination of cues embedded in the context of coreferent mentions; and (3) A plethora of existing MRC datasets can be used for data augmentation to improve the model's generalization capability. Experiments demonstrate significant performance boost over previous models, with 87.5 (+2.5) F1 score on the GAP benchmark and 83.1 (+3.5) F1 score on the CoNLL-2012 benchmark.