Coreference Resolution: Are the Eliminated Spans Totally Worthless?

Up to date, various neural-based methods have been proposed for joint mention span detection and coreference resolution. However, existing studies on coreference resolution mainly depend on mention representations, while the rest spans in the text are largely ignored and directly eliminated. In this paper, we aim at investigating whether those eliminated spans are totally worthless, or to what extent they can help improve the performance of coreference resolution. To achieve this goal, we propose to refine the representation of mentions with global spans including these eliminated ones leveraged. On this basis, we further introduce an additional loss term in this work to encourage the diversity between different entity clusters. Experimental results on the documentlevel CoNLL-2012 Shared Task English dataset show that the eliminated spans are indeed useful and our proposed approaches show promising results in coreference resolution.

[1]  Pascal Denis,et al.  A Ranking Approach to Pronoun Resolution , 2007, IJCAI.

[2]  Claire Gardent,et al.  Improving Machine Learning Approaches to Coreference Resolution , 2002, ACL.

[3]  Jian Fu,et al.  Incorporating Structural Information for Better Coreference Resolution , 2019, IJCAI.

[4]  Luke S. Zettlemoyer,et al.  End-to-end Neural Coreference Resolution , 2017, EMNLP.

[5]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[6]  Christopher D. Manning,et al.  Entity-Centric Coreference Resolution with Model Stacking , 2015, ACL.

[7]  Jiwei Li,et al.  CorefQA: Coreference Resolution as Query-based Span Prediction , 2020, ACL.

[8]  Lynette Hirschman,et al.  A Model-Theoretic Coreference Scoring Scheme , 1995, MUC.

[9]  Dan Roth,et al.  Understanding the Value of Features for Coreference Resolution , 2008, EMNLP.

[10]  Jason Weston,et al.  Learning Anaphoricity and Antecedent Ranking Features for Coreference Resolution , 2015, ACL.

[11]  Luke S. Zettlemoyer,et al.  Deep Contextualized Word Representations , 2018, NAACL.

[12]  Navdeep Jaitly,et al.  Pointer Networks , 2015, NIPS.

[13]  Alexander M. Rush,et al.  Learning Global Features for Coreference Resolution , 2016, NAACL.

[14]  Rui Zhang,et al.  Neural Coreference Resolution with Deep Biaffine Attention by Joint Mention Detection and Mention Clustering , 2018, ACL.

[15]  Omer Levy,et al.  BERT for Coreference Resolution: Baselines and Analysis , 2019, EMNLP/IJCNLP.

[16]  Xu Li,et al.  End-to-end Deep Reinforcement Learning Based Coreference Resolution , 2019, ACL.

[17]  Yoshua Bengio,et al.  Word Representations: A Simple and General Method for Semi-Supervised Learning , 2010, ACL.

[18]  Breck Baldwin,et al.  Algorithms for Scoring Coreference Chains , 1998 .

[19]  Xiaoqiang Luo,et al.  On Coreference Resolution Performance Metrics , 2005, HLT.

[20]  Yuchen Zhang,et al.  CoNLL-2012 Shared Task: Modeling Multilingual Unrestricted Coreference in OntoNotes , 2012, EMNLP-CoNLL Shared Task.

[21]  Amir Globerson,et al.  Coreference Resolution with Entity Equalization , 2019, ACL.

[22]  Christopher D. Manning,et al.  Improving Coreference Resolution by Learning Entity-Level Distributed Representations , 2016, ACL.

[23]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[24]  Luke S. Zettlemoyer,et al.  Higher-Order Coreference Resolution with Coarse-to-Fine Inference , 2018, NAACL.

[25]  Christopher D. Manning,et al.  Deep Reinforcement Learning for Mention-Ranking Coreference Models , 2016, EMNLP.