CorefQA: Coreference Resolution as Query-based Span Prediction

Wei Wu, Fei Wang, Arianna Yuan, Fei Wu, Jiwei Li

Abstract Paper Share

NLP Applications Long Paper

Session 12A: Jul 8 (08:00-09:00 GMT)
Session 13A: Jul 8 (12:00-13:00 GMT)
Abstract: 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.
You can open the pre-recorded video in a separate window.
NOTE: The SlidesLive video may display a random order of the authors. The correct author list is shown at the top of this webpage.

Similar Papers

SpanBERT: Improving Pre-training by Representing and Predicting Spans
Mandar Joshi, Danqi Chen, Yinhan Liu, Daniel S. Weld, Luke Zettlemoyer, Omer Levy,
A representative figure from paper tacl.1853
Active Learning for Coreference Resolution using Discrete Annotation
Belinda Z. Li, Gabriel Stanovsky, Luke Zettlemoyer,
A representative figure from paper main.738
Span-based Localizing Network for Natural Language Video Localization
Hao Zhang, Aixin Sun, Wei Jing, Joey Tianyi Zhou,
A representative figure from paper main.585