An Example-Based Approach to Difficult Pronoun Resolution

A Winograd schema is a pair of twin sentences containing a referential ambiguity that is easy for a human to resolve but difficult for a computer. This paper explores the characteristics of world knowledge necessary for resolving such a schema. We observe that people tend to avoid ambiguous antecedents when using pronouns in writing. We present a method for automatically acquiring examples that are similar to Winograd schemas but have less ambiguity. We generate a concise search query that captures the essential parts of a given source sentence and then find the alignments of the source sentence and its retrieved examples. Our experimental results show that the existing sentences on the Web indeed contain instances of world knowledge useful for difficult pronoun resolution.

[1]  Nianwen Xue,et al.  CoNLL-2011 Shared Task: Modeling Unrestricted Coreference in OntoNotes , 2011, CoNLL Shared Task.

[2]  Hector J. Levesque,et al.  On our best behaviour , 2014, Artif. Intell..

[3]  Christopher D. Manning,et al.  Generating Typed Dependency Parses from Phrase Structure Parses , 2006, LREC.

[4]  Jeffrey L. Elman,et al.  Coherence and Coreference Revisited , 2007, J. Semant..

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

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

[7]  Terry Winograd,et al.  Understanding natural language , 1974 .

[8]  Varol Akman,et al.  Book Review -- Hans Kamp and Uwe Reyle, From Discourse to Logic: Introduction to Model-theoretic Semantics of Natural Language, Formal Logic and Discourse Representation Theory , 1995 .

[9]  Vincent Ng,et al.  Resolving Complex Cases of Definite Pronouns: The Winograd Schema Challenge , 2012, EMNLP.

[10]  Michael Collins,et al.  Head-Driven Statistical Models for Natural Language Parsing , 2003, CL.

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

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

[13]  Philipp Koehn,et al.  Abstract Meaning Representation for Sembanking , 2013, LAW@ACL.

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

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

[16]  Jerry R. Hobbs.  Coherence and Coreference , 1979, Cogn. Sci..

[17]  Hannah Rohde,et al.  A probabilistic reconciliation of coherence-driven and centering-driven theories of pronoun interpretation , 2013 .

[18]  Uwe Reyle,et al.  From Discourse to Logic - Introduction to Modeltheoretic Semantics of Natural Language, Formal Logic and Discourse Representation Theory , 1993, Studies in linguistics and philosophy.

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

[20]  Martin Kay,et al.  Syntactic Process , 1979, ACL.

[21]  Hector J. Levesque,et al.  The Winograd Schema Challenge , 2011, AAAI Spring Symposium: Logical Formalizations of Commonsense Reasoning.

[22]  Dan Flickinger,et al.  Minimal Recursion Semantics: An Introduction , 2005 .

[23]  Ewan Klein,et al.  Natural Language Processing with Python , 2009 .

[24]  Heeyoung Lee,et al.  A Multi-Pass Sieve for Coreference Resolution , 2010, EMNLP.

[25]  Nathanael Chambers,et al.  Unsupervised Learning of Narrative Event Chains , 2008, ACL.

[26]  Peter D. Turney.  Similarity of Semantic Relations , 2006, CL.

[27]  Oren Etzioni,et al.  Generating Coherent Event Schemas at Scale , 2013, EMNLP.

[28]  Dan Klein,et al.  Learning Dependency-Based Compositional Semantics , 2011, CL.

[29]  Heng Ji,et al.  Gender and Animacy Knowledge Discovery from Web-Scale N-Grams for Unsupervised Person Mention Detection , 2009, PACLIC.