Modelling Pro-drop with the Rational Speech Acts Model

We extend the classic Referring Expressions Generation task by considering zero pronouns in pro-drop languages such as Chinese, modelling their use by means of the Bayesian Rational Speech Acts model. By assuming that highly salient referents are most likely to be referred to by zero pronouns (i.e., pro-drop is more likely for salient referents than the less salient ones), the model offers an attractive explanation of a phenomenon not previously addressed probabilistically.

[1]  Michael C. Frank,et al.  Predicting Pragmatic Reasoning in Language Games , 2012, Science.

[2]  Christopher Potts,et al.  Generating Bilingual Pragmatic Color References , 2018, NAACL.

[3]  Ehud Reiter,et al.  Book Reviews: Building Natural Language Generation Systems , 2000, CL.

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

[5]  Christopher Potts,et al.  Learning in the Rational Speech Acts Model , 2015, ArXiv.

[6]  Allyson Ettinger,et al.  Dialogue focus tracking for zero pronoun resolution , 2015, NAACL.

[7]  Teruaki Aizawa,et al.  Centering as an Anaphora Generation Algorithm: A Language Learning Aid Perspective , 2001, NLPRS.

[8]  Christopher Potts,et al.  Colors in Context: A Pragmatic Neural Model for Grounded Language Understanding , 2017, TACL.

[9]  Shuming Shi,et al.  Translating Pro-Drop Languages with Reconstruction Models , 2018, AAAI.

[10]  Chris Mellish,et al.  An Empirical Study on the Generation of Anaphora in Chinese , 1997, Comput. Linguistics.

[11]  Yu Zhang,et al.  Deep Reinforcement Learning for Chinese Zero Pronoun Resolution , 2018, ACL.

[12]  Weinan Zhang,et al.  Chinese Zero Pronoun Resolution with Deep Memory Network , 2017, EMNLP.

[13]  Kees van Deemter.  Computational Models of Referring: A Study in Cognitive Science , 2016 .

[14]  S. Brennan.  Centering Attention in Discourse. , 1995 .

[15]  Matthew P. Aylett,et al.  Referential form, word duration, and modelling the listener in spoken dialogue , 2004 .

[16]  Chen Chen,et al.  Chinese Zero Pronoun Resolution: A Joint Unsupervised Discourse-Aware Model Rivaling State-of-the-Art Resolvers , 2015, ACL.

[17]  曹 逢甫,et al.  A functional study of topic in Chinese : the first step towards discourse analysis , 1979 .

[18]  Chen Chen,et al.  Chinese Zero Pronoun Resolution with Deep Neural Networks , 2016, ACL.

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

[20]  Naomi Feldman,et al.  Why discourse affects speakers’ choice of referring expressions , 2015, ACL.

[21]  Thomas Hofmann,et al.  Speakers optimize information density through syntactic reduction , 2007 .

[22]  Ji-Eun Roh,et al.  An empirical study for generating zero pronoun in Korean based on Cost-based centering model , 2003, ALTA.

[23]  Brady Clark,et al.  Communicating with Cost-based Implicature: a Game-Theoretic Approach to Ambiguity , 2012 .

[24]  T. Givon.  Topic Continuity in Discourse , 1983 .

[25]  Weinan Zhang,et al.  A Deep Neural Network for Chinese Zero Pronoun Resolution , 2016, IJCAI.

[26]  C. Huang,et al.  Pro-Drop in Chinese: A Generalized Control Theory , 1989 .

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

[28]  C. Huang.  On the distribution and reference of empty pronouns , 1984 .

[29]  W. Chafe.  Discourse, Consciousness, and Time: The Flow and Displacement of Conscious Experience in Speaking and Writing , 1996 .

[30]  Andy Way,et al.  A Novel Approach to Dropped Pronoun Translation , 2016, NAACL.

[31]  Chen Chen,et al.  Chinese Zero Pronoun Resolution: An Unsupervised Approach Combining Ranking and Integer Linear Programming , 2014, AAAI.