A Global Relaxation Labeling Approach to Coreference Resolution

This paper presents a constraint-based graph partitioning approach to coreference resolution solved by relaxation labeling. The approach combines the strengths of groupwise classifiers and chain formation methods in one global method. Experiments show that our approach significantly outperforms systems based on separate classification and chain formation steps, and that it achieves the best results in the state of the art for the same dataset and metrics.

[1]  Andrew McCallum,et al.  First-Order Probabilistic Models for Coreference Resolution , 2007, NAACL.

[2]  Carme Torras.  Relaxation and Neural Learning: Points of Convergence and Divergence , 1989, J. Parallel Distributed Comput..

[3]  Pascal Denis,et al.  Specialized Models and Ranking for Coreference Resolution , 2008, EMNLP.

[4]  Jordi Atserias Batalla.  Towards robustness in natural language understanding , 2006 .

[5]  Steven W. Zucker,et al.  On the Foundations of Relaxation Labeling Processes , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

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

[8]  Xiaoqiang Luo,et al.  On Coreference Resolution Performance Metrics , 2005, HLT.

[9]  Martin C. Herbordt,et al.  A System for Evaluating Performance and Cost of SIMD Array Designs , 2000, J. Parallel Distributed Comput..

[10]  Breck Baldwin,et al.  Algorithms for Scoring Coreference Chains , 1998 .

[11]  Horacio Rodríguez,et al.  A Machine Learning Approach to POS Tagging , 2000, Machine Learning.

[12]  Lluís Padró,et al.  FreeLing 1.3: Syntactic and semantic services in an open-source NLP library , 2006, LREC.

[13]  Mihai Surdeanu,et al.  Named entity recognition from spontaneous open-domain speech , 2005, INTERSPEECH.

[14]  Manfred Klenner,et al.  Optimization in Coreference Resolution is not Needed: A Nearly-Optimal Algorithm with Intensional Constraints , 2009, EACL.

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

[16]  Ricardo Baeza Yates,et al.  Lenguajes y Sistemas Informáticos , 2002 .

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

[18]  Manfred Klenner,et al.  Enhancing coreference clustering , 2008 .

[19]  Lluís Màrquez i Villodre,et al.  SVMTool: A general POS Tagger Generator Based on Support Vector Machines , 2004, LREC.

[20]  Veronique Hoste,et al.  Optimization issues in machine learning of coreference resolution , 2005 .

[21]  Claire Gardent,et al.  Improving Machine Learning Approaches to Coreference Resolution , 2002, ACL.

[22]  Wendy G. Lehnert,et al.  Using Decision Trees for Coreference Resolution , 1995, IJCAI.

[23]  Lluís Padró,et al.  RelaxCor: A Global Relaxation Labeling Approach to Coreference Resolution , 2010, ACL 2010.

[24]  Christopher D. Manning,et al.  Enforcing Transitivity in Coreference Resolution , 2008, ACL.

[25]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[26]  Manfred Klenner.  Enforcing Consistency on Coreference Sets , 2007 .

[27]  Marcello Pelillo,et al.  The Dynamics of Nonlinear Relaxation Labeling Processes , 1997, Journal of Mathematical Imaging and Vision.

[28]  Jian Su,et al.  Coreference Resolution Using Competition Learning Approach , 2003, ACL.

[29]  Yannick Versley,et al.  SemEval-2010 Task 1: Coreference Resolution in Multiple Languages , 2009, *SEMEVAL.

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

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

[32]  Xiaoqiang Luo.  Coreference or Not: A Twin Model for Coreference Resolution , 2007, HLT-NAACL.

[33]  Pascal Denis,et al.  New learning models for robust reference resolution , 2007 .

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

[35]  Scott Bennett,et al.  Evaluating Automated and Manual Acquisition of Anaphora Resolution Strategies , 1995, ACL.