CorefQA: Coreference Resolution as Query-based Span Prediction

ACL 2020  ·  Wei Wu, Fei Wang, Arianna Yuan, Fei Wu, Jiwei Li ·

In this paper, we present CorefQA, an accurate and extensible approach for the coreference resolution task. We formulate the problem as a span prediction task, like in question answering: 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 question answering 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 question answering datasets can be used for data augmentation to improve the model{'}s generalization capability. Experiments demonstrate significant performance boost over previous models, with 83.1 (+3.5) F1 score on the CoNLL-2012 benchmark and 87.5 (+2.5) F1 score on the GAP benchmark. read more

PDF Abstract ACL 2020 PDF ACL 2020 Abstract

Datasets


Results from the Paper


 Ranked #1 on Coreference Resolution on CoNLL 2012 (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Benchmark
Coreference Resolution CoNLL 2012 CorefQA + SpanBERT-base Avg F1 79.9 # 3
Coreference Resolution CoNLL 2012 CorefQA + SpanBERT-large Avg F1 83.1 # 1

Methods


No methods listed for this paper. Add relevant methods here