Chinese Zero Pronoun Resolution: An Unsupervised Probabilistic Model Rivaling Supervised Resolvers

State-of-the-art Chinese zero pronoun resolution systems are supervised, thus relying on training data containing manually resolved zero pronouns. To eliminate the reliance on annotated data, we present a generative model for unsupervised Chinese zero pronoun resolution. At the core of our model is a novel hypothesis: a probabilistic pronoun resolver trained on overt pronouns in an unsupervised manner can be used to resolve zero pronouns. Experiments demonstrate that our unsupervised model rivals its state-ofthe-art supervised counterparts in performance when resolving the Chinese zero pronouns in the OntoNotes corpus.

[1]  Fang Kong,et al.  A Tree Kernel-Based Unified Framework for Chinese Zero Anaphora Resolution , 2010, EMNLP.

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

[3]  Martha Palmer,et al.  Korean zero pronouns: analysis and resolution , 2006 .

[4]  Tomoko Izumi,et al.  Discriminative Approach to Predicate-Argument Structure Analysis with Zero-Anaphora Resolution , 2009, ACL.

[5]  Kazuhiro Seki,et al.  A Probabilistic Method for Analyzing Japanese Anaphora Integrating Zero Pronoun Detection and Resolution , 2002, COLING.

[6]  Yi-Chun Chen,et al.  Zero Anaphora Resolution in Chinese with Shallow Parsing , 2007, J. Chin. Lang. Comput..

[7]  Jian Su,et al.  Improving Pronoun Resolution Using Statistics-Based Semantic Compatibility Information , 2005, ACL.

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

[9]  Hwee Tou Ng,et al.  Identification and Resolution of Chinese Zero Pronouns: A Machine Learning Approach , 2007, EMNLP.

[10]  Micha Elsner,et al.  EM Works for Pronoun Anaphora Resolution , 2009, EACL.

[11]  Colin Cherry,et al.  An Expectation Maximization Approach to Pronoun Resolution , 2005, CoNLL.

[12]  Martha Palmer,et al.  Pronominal anaphora resolution in chinese , 2006 .

[13]  Yuji Matsumoto,et al.  Zero-anaphora resolution by learning rich syntactic pattern features , 2007, TALIP.

[14]  Antonio Ferrández Rodríguez,et al.  A Computational Approach to Zero-pronouns in Spanish , 2000, ACL.

[15]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[16]  Chen Chen,et al.  Chinese Zero Pronoun Resolution: Some Recent Advances , 2013, EMNLP.

[17]  Sadao Kurohashi,et al.  A Discriminative Approach to Japanese Zero Anaphora Resolution with Large-scale Lexicalized Case Frames , 2011, IJCNLP.

[18]  Douglas E. Appelt,et al.  The (Non)Utility of Predicate-Argument Frequencies for Pronoun Interpretation , 2004, NAACL.

[19]  Scott Weinstein,et al.  Centering: A Framework for Modeling the Local Coherence of Discourse , 1995, CL.

[20]  Xuanjing Huang,et al.  2D Trie for Fast Parsing , 2010, COLING.

[21]  Chen Chen,et al.  SinoCoreferencer: An End-to-End Chinese Event Coreference Resolver , 2014, LREC.

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

[23]  Massimo Poesio,et al.  A Cross-Lingual ILP Solution to Zero Anaphora Resolution , 2011, ACL.

[24]  Tsutomu Hirao,et al.  Japanese Zero Pronoun Resolution based on Ranking Rules and Machine Learning , 2003, EMNLP.

[25]  Fang Kong,et al.  Context-Sensitive Convolution Tree Kernel for Pronoun Resolution , 2008, IJCNLP.

[26]  Yuji Matsumoto,et al.  Exploiting Syntactic Patterns as Clues in Zero-Anaphora Resolution , 2006, ACL.