Accurate Semantic Class Classifier for Coreference Resolution

There have been considerable attempts to incorporate semantic knowledge into coreference resolution systems: different knowledge sources such as WordNet and Wikipedia have been used to boost the performance. In this paper, we propose new ways to extract WordNet feature. This feature, along with other features such as named entity feature, can be used to build an accurate semantic class (SC) classifier. In addition, we analyze the SC classification errors and propose to use relaxed SC agreement features. The proposed accurate SC classifier and the relaxation of SC agreement features on ACE2 coreference evaluation can boost our baseline system by 10.4% and 9.7% using MUC score and anaphor accuracy respectively.

[1]  C. Fellbaum.  An Electronic Lexical Database , 1998 .

[2]  Simone Paolo Ponzetto,et al.  Exploiting Semantic Role Labeling, WordNet and Wikipedia for Coreference Resolution , 2006, NAACL.

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

[4]  Dan Klein,et al.  Optimization, Maxent Models, and Conditional Estimation without Magic , 2003, NAACL.

[5]  Imed Zitouni,et al.  Factorizing Complex Models: A Case Study in Mention Detection , 2006, ACL.

[6]  Renata Vieira,et al.  An Empirically-based System for Processing Definite Descriptions , 2000, CL.

[7]  Andrew McCallum,et al.  Conditional Models of Identity Uncertainty with Application to Noun Coreference , 2004, NIPS.

[8]  Tony Veale,et al.  An Intrinsic Information Content Metric for Semantic Similarity in WordNet , 2004, ECAI.

[9]  Vincent Ng,et al.  Shallow Semantics for Coreference Resolution , 2007, IJCAI.

[10]  Cristina Nicolae,et al.  BESTCUT: A Graph Algorithm for Coreference Resolution , 2006, EMNLP.

[11]  Xiaoqiang Luo,et al.  A Mention-Synchronous Coreference Resolution Algorithm Based On the Bell Tree , 2004, ACL.

[12]  Lynette Hirschman,et al.  A Model-Theoretic Coreference Scoring Scheme , 1995, MUC.

[13]  Sanda M. Harabagiu,et al.  RESOLUTION , 1977, Monatsschrift für Kriminologie und Strafrechtsreform.

[14]  Treebank Penn,et al.  Linguistic Data Consortium , 1999 .

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

[16]  Pascal Denis,et al.  Joint Determination of Anaphoricity and Coreference Resolution using Integer Programming , 2007, NAACL.

[17]  Daniel Marcu,et al.  A Large-Scale Exploration of Effective Global Features for a Joint Entity Detection and Tracking Model , 2005, HLT.

[18]  Hwee Tou Ng,et al.  A Machine Learning Approach to Coreference Resolution of Noun Phrases , 2001, CL.

[19]  Yannick Versley,et al.  BART: A Modular Toolkit for Coreference Resolution , 2008, ACL.

[20]  Dekang Lin.  Using Collocation Statistics in Information Extraction , 1998, MUC.

[21]  Vincent Ng,et al.  Semantic Class Induction and Coreference Resolution , 2007, ACL.

[22]  Malvina Nissim,et al.  Comparing Knowledge Sources for Nominal Anaphora Resolution , 2005, Computational Linguistics.

[23]  Dekang Lin,et al.  Automatic Retrieval and Clustering of Similar Words , 1998, ACL.

[24]  Massimo Poesio,et al.  Learning to Resolve Bridging References , 2004, ACL.

[25]  Jian Su,et al.  Coreference Resolution Using Semantic Relatedness Information from Automatically Discovered Patterns , 2007, ACL.

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

[27]  Adam L. Berger,et al.  A Maximum Entropy Approach to Natural Language Processing , 1996, CL.