A Unified Event Coreference Resolution by Integrating Multiple Resolvers

Event coreference is an important and complicated task in cascaded event template extraction and other natural language processing tasks. Despite its importance, it was merely discussed in previous studies. In this paper, we present a globally optimized coreference resolution system dedicated to various sophisticated event coreference phenomena. Seven resolvers for both event and object coreference cases are utilized, which include three new resolvers for event coreference resolution. Three enhancements are further proposed at both mention pair detection and chain formation levels. First, the object coreference resolvers are used to effectively reduce the false positive cases for event coreference. Second, A revised instance selection scheme is proposed to improve link level mention-pair model performances. Last but not least, an efficient and globally optimized graph partitioning model is employed for coreference chain formation using spectral partitioning which allows the incorporation of pronoun coreference information. The three techniques contribute to a significant improvement of 8.54% in B 3 F-score for event coreference resolution on OntoNotes 2.0 corpus.

[1]  Ulrike von Luxburg,et al.  A tutorial on spectral clustering , 2007, Stat. Comput..

[2]  Candace L. Sidner,et al.  Focusing in the comprehension of definite anaphora , 1986 .

[3]  Claire Cardie,et al.  Combining Sample Selection and Error-Driven Pruning for Machine Learning of Coreference Rules , 2002, EMNLP.

[4]  Claire Cardie,et al.  Coreference Resolution with Reconcile , 2010, ACL.

[5]  Nicholas Asher,et al.  Reference to abstract objects in discourse , 1993, Studies in linguistics and philosophy.

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

[7]  Roded Sharan,et al.  Algorithmic approaches to clustering gene expression data , 2001 .

[8]  Christoph Müller.  Resolving It, This, and That in Unrestricted Multi-Party Dialog , 2007, ACL.

[9]  Pedro M. Domingos,et al.  Joint Unsupervised Coreference Resolution with Markov Logic , 2008, EMNLP.

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

[11]  Michael Strube,et al.  End-to-End Coreference Resolution via Hypergraph Partitioning , 2010, COLING.

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

[13]  Jian Su,et al.  A Twin-Candidate Based Approach for Event Pronoun Resolution using Composite Kernel , 2010, COLING.

[14]  Michael I. Jordan,et al.  On Spectral Clustering: Analysis and an algorithm , 2001, NIPS.

[15]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

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

[17]  Sameer Pradhan,et al.  Unrestricted Coreference: Identifying Entities and Events in OntoNotes , 2007, International Conference on Semantic Computing (ICSC 2007).

[18]  Donna K. Byron,et al.  Resolving Pronominal Reference to Abstract Entities , 2002, ACL.

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