Addressing the Winograd Schema Challenge as a Sequence Ranking Task

The Winograd Schema Challenge targets pronominal anaphora resolution problems which require the application of cognitive inference in combination with world knowledge. These problems are easy to solve for humans but most difficult to solve for machines. Computational models that previously addressed this task rely on syntactic preprocessing and incorporation of external knowledge by manually crafted features. We address the Winograd Schema Challenge from a new perspective as a sequence ranking task, and design a Siamese neural sequence ranking model which performs significantly better than a random baseline, even when solely trained on sequences of words. We evaluate against a baseline and a state-of-the-art system on two data sets and show that anonymization of noun phrase candidates strongly helps our model to generalize.

[1]  Christopher Potts,et al.  A large annotated corpus for learning natural language inference , 2015, EMNLP.

[2]  Chitta Baral,et al.  Towards Addressing the Winograd Schema Challenge - Building and Using a Semantic Parser and a Knowledge Hunting Module , 2015, IJCAI.

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

[4]  Sepp Hochreiter,et al.  Self-Normalizing Neural Networks , 2017, NIPS.

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

[6]  Yejin Choi,et al.  Connotation Frames: A Data-Driven Investigation , 2015, ACL.

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

[8]  Alex M. Andrew,et al.  Knowledge Representation, Reasoning and Declarative Problem Solving , 2004 .

[9]  Holger Schwenk,et al.  Supervised Learning of Universal Sentence Representations from Natural Language Inference Data , 2017, EMNLP.

[10]  John B. Lowe,et al.  The Berkeley FrameNet Project , 1998, ACL.

[11]  Jiri Matas,et al.  All you need is a good init , 2015, ICLR.

[12]  David K. Smith.  Theory of Linear and Integer Programming , 1987 .

[13]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[14]  Surya Ganguli,et al.  Exact solutions to the nonlinear dynamics of learning in deep linear neural networks , 2013, ICLR.

[15]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[16]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[17]  Catherine Havasi,et al.  Representing General Relational Knowledge in ConceptNet 5 , 2012, LREC.

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

[19]  Dan Roth,et al.  A Joint Framework for Coreference Resolution and Mention Head Detection , 2015, CoNLL.

[20]  Kentaro Inui,et al.  An Example-Based Approach to Difficult Pronoun Resolution , 2014, PACLIC.

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

[22]  Yejin Choi,et al.  Connotation Frames: Typed Relations of Implied Sentiment in Predicate-Argument Structure , 2015, ArXiv.

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

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

[25]  Luke S. Zettlemoyer,et al.  End-to-end Neural Coreference Resolution , 2017, EMNLP.

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

[27]  Peter Schüller,et al.  Tackling Winograd Schemas by Formalizing Relevance Theory in Knowledge Graphs , 2014, KR.

[28]  Robyn Speer,et al.  ConceptNet at SemEval-2017 Task 2: Extending Word Embeddings with Multilingual Relational Knowledge , 2017, *SEMEVAL.