Graph-based event coreference resolution

Zheng Chen, Heng Ji

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In contrast to entity coreference resolution, event coreference resolution has not received great attention from researchers. In this paper, we first demonstrate the diverse scenarios of event coreference by an example. We then model event coreference resolution as a spectral graph clustering problem and evaluate the clustering algorithm on ground truth event mentions using ECM F-Measure. We obtain the ECM-F scores of 0.8363 and 0.8312 respectively by using two methods for computing coreference matrices.

Original languageEnglish (US)
Title of host publicationACL-IJCNLP 2009 - TextGraphs 2009
Subtitle of host publication2009 Workshop on Graph-Based Methods for Natural Language Processing, Proceedings of the Workshop
PublisherAssociation for Computational Linguistics (ACL)
Pages54-57
Number of pages4
ISBN (Print)193243254X, 9781932432541
DOIs
StatePublished - 2009
Externally publishedYes
Event4th Workshop on Graph-Based Methods for Natural Language Processing, TextGraphs 2009 - Suntec, Singapore
Duration: Aug 7 2009Aug 7 2009

Publication series

NameACL-IJCNLP 2009 - TextGraphs 2009: 2009 Workshop on Graph-Based Methods for Natural Language Processing, Proceedings of the Workshop

Conference

Conference4th Workshop on Graph-Based Methods for Natural Language Processing, TextGraphs 2009
Country/TerritorySingapore
CitySuntec
Period8/7/098/7/09

ASJC Scopus subject areas

  • Software

Fingerprint

Dive into the research topics of 'Graph-based event coreference resolution'. Together they form a unique fingerprint.

Cite this