Exophoric Pronoun Resolution in Dialogues with Topic Regularization

Resolving pronouns to their referents has long been studied as a fundamental natural language understanding problem. Previous works on pronoun coreference resolution (PCR) mostly focus on resolving pronouns to mentions in text while ignoring the exophoric scenario. Exophoric pronouns are common in daily communications, where speakers may directly use pronouns to refer to some objects present in the environment without introducing the objects first. Although such objects are not mentioned in the dialogue text, they can often be disambiguated by the general topics of the dialogue. Motivated by this, we propose to jointly leverage the local context and global topics of dialogues to solve the out-of-text PCR problem. Extensive experiments demonstrate the effectiveness of adding topic regularization for resolving exophoric pronouns.

[1]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[2]  Liane Guillou,et al.  Improving Pronoun Translation for Statistical Machine Translation , 2012, EACL.

[3]  José M. F. Moura,et al.  Visual Dialog , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  José M. F. Moura,et al.  Visual Coreference Resolution in Visual Dialog using Neural Module Networks , 2018, ECCV.

[5]  Jorge Hankamer,et al.  Deep and surface anaphora , 1993 .

[6]  S. Reeves,et al.  Discourse Analysis , 2018, The Study of Language.

[7]  Omer Levy,et al.  SpanBERT: Improving Pre-training by Representing and Predicting Spans , 2019, TACL.

[8]  Yan Song,et al.  Incorporating Context and External Knowledge for Pronoun Coreference Resolution , 2019, NAACL.

[9]  Daisuke Kawahara,et al.  Japanese Zero Reference Resolution Considering Exophora and Author/Reader Mentions , 2013, EMNLP.

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

[11]  Ruslan Mitkov,et al.  Robust Pronoun Resolution with Limited Knowledge , 1998, ACL.

[12]  Pragmatically controlled anaphora , 1979 .

[13]  Manfred Stede,et al.  Anaphora Resolution for Twitter Conversations: An Exploratory Study , 2018 .

[14]  Michael Halliday,et al.  Cohesion in English , 1976 .

[15]  Noah A. Smith,et al.  Quoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning , 2019, EMNLP.

[16]  Michael Strube,et al.  A Machine Learning Approach to Pronoun Resolution in Spoken Dialogue , 2003, ACL.

[17]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

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

[19]  Hongming Zhang,et al.  Joint Coreference Resolution and Character Linking for Multiparty Conversation , 2021, EACL.

[20]  Yan Song,et al.  What You See is What You Get: Visual Pronoun Coreference Resolution in Dialogues , 2019, EMNLP.

[21]  Karel Jezek,et al.  Two uses of anaphora resolution in summarization , 2007, Inf. Process. Manag..

[22]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[23]  Kate Ehrlich,et al.  Search and Inference Strategies in Pronoun Resolution: an Experimental Study , 1981, ACL.

[24]  Vincent Ng Supervised Ranking for Pronoun Resolution: Some Recent Improvements , 2005, AAAI.

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

[26]  Zhiwu Lu,et al.  Recursive Visual Attention in Visual Dialog , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

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

[29]  Steven Bird,et al.  NLTK: The Natural Language Toolkit , 2002, ACL.

[30]  Gholamreza Haffari,et al.  Contextual Neural Machine Translation Improves Translation of Cataphoric Pronouns , 2020, ACL.