The More Antecedents, the Merrier: Resolving Multi-Antecedent Anaphors

Anaphor resolution is an important task in NLP with many applications. Despite much research effort, it remains an open problem. The difficulty of the problem varies substantially across different sub-problems. One sub-problem, in particular, has been largely untouched by prior work despite occurring frequently throughout corpora: the anaphor that has multiple antecedents, which here we call multi-antecedent anaphors or manaphors. Current coreference resolvers restrict anaphors to at most a single antecedent. As we show in this paper, relaxing this constraint poses serious problems in coreference chain-building, where each chain is intended to refer to a single entity. This work provides a formalization of the new task with preliminary insights into multi-antecedent noun-phrase anaphors, and offers a method for resolving such cases that outperforms a number of baseline methods by a significant margin. Our system uses local agglomerative clustering on candidate antecedents and an existing coreference system to score clusters to determine which cluster of mentions is antecedent for a given anaphor. When we augment an existing coreference system with our proposed method, we observe a substantial increase in performance (0.6 absolute CoNLL F1) on an annotated

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

[2]  Pascal Denis,et al.  Joint Determination of Anaphoricity and Coreference Resolution using Integer Programming , 2007, NAACL.

[3]  Mitchell P. Marcus,et al.  OntoNotes: The 90% Solution , 2006, NAACL.

[4]  David Stallard,et al.  A Computational Mechanism for Pronominal Reference , 1989, ACL.

[5]  Claire Cardie,et al.  Reconcile: A Coreference Resolution Research Platform , 2010 .

[6]  Richárd Farkas,et al.  Data-driven Multilingual Coreference Resolution using Resolver Stacking , 2012, EMNLP-CoNLL Shared Task.

[7]  Dan Klein,et al.  Error-Driven Analysis of Challenges in Coreference Resolution , 2013, EMNLP.

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

[9]  Dan Roth,et al.  Solving Hard Coreference Problems , 2019, NAACL.

[10]  Dan Klein,et al.  Easy Victories and Uphill Battles in Coreference Resolution , 2013, EMNLP.

[11]  Vincent Ng,et al.  Supervised Noun Phrase Coreference Research: The First Fifteen Years , 2010, ACL.

[12]  Daniel Jurafsky,et al.  Same Referent, Different Words: Unsupervised Mining of Opaque Coreferent Mentions , 2013, NAACL.

[13]  Edith Bolling Anaphora Resolution , 2006 .

[14]  Dekang Lin,et al.  Bootstrapping Path-Based Pronoun Resolution , 2006, ACL.

[15]  Mark A. Przybocki,et al.  The Automatic Content Extraction (ACE) Program – Tasks, Data, and Evaluation , 2004, LREC.

[16]  Hwee Tou Ng,et al.  A Machine Learning Approach to Coreference Resolution of Noun Phrases , 2001, CL.

[17]  Claire Cardie,et al.  Identifying Anaphoric and Non-Anaphoric Noun Phrases to Improve Coreference Resolution , 2002, COLING.

[18]  Heeyoung Lee,et al.  Stanford’s Multi-Pass Sieve Coreference Resolution System at the CoNLL-2011 Shared Task , 2011, CoNLL Shared Task.

[19]  Srinivas Bangalore,et al.  Exploiting a Probabilistic Hierarchical Model for Generation , 2000, COLING.

[20]  Mihai Surdeanu,et al.  The Stanford CoreNLP Natural Language Processing Toolkit , 2014, ACL.

[21]  Kevin Knight,et al.  Generation that Exploits Corpus-Based Statistical Knowledge , 1998, ACL.

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

[23]  Sampo Pyysalo,et al.  brat: a Web-based Tool for NLP-Assisted Text Annotation , 2012, EACL.

[24]  Alessandro Moschitti,et al.  Making Tree Kernels Practical for Natural Language Learning , 2006, EACL.

[25]  Vincent Ng,et al.  Unsupervised Models for Coreference Resolution , 2008, EMNLP.

[26]  Pierre Nugues,et al.  Exploring Lexicalized Features for Coreference Resolution , 2011, CoNLL Shared Task.

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

[28]  Eduard H. Hovy,et al.  A Deeper Look into Features for Coreference Resolution , 2009, DAARC.

[29]  Christopher D. Manning,et al.  Incorporating Non-local Information into Information Extraction Systems by Gibbs Sampling , 2005, ACL.

[30]  Jerry R. Hobbs Resolving pronoun references , 1986 .

[31]  Christopher Potts,et al.  The Life and Death of Discourse Entities: Identifying Singleton Mentions , 2013, NAACL.

[32]  Derek Ruths,et al.  Mr. Bennet, his coachman, and the Archbishop walk into a bar but only one of them gets recognized: On The Difficulty of Detecting Characters in Literary Texts , 2015, EMNLP.

[33]  Michael Collins,et al.  New Ranking Algorithms for Parsing and Tagging: Kernels over Discrete Structures, and the Voted Perceptron , 2002, ACL.

[34]  Megumi Kameyama,et al.  Recognizing referential links: an information extraction prespective , 1997, ArXiv.

[35]  Claire Cardie,et al.  Conundrums in Noun Phrase Coreference Resolution: Making Sense of the State-of-the-Art , 2009, ACL.

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

[37]  Kees van Deemter,et al.  On Coreferring: Coreference in MUC and Related Annotation Schemes , 2000, CL.

[38]  Kate Saenko,et al.  Generating Natural-Language Video Descriptions Using Text-Mined Knowledge , 2013, AAAI.