A Pairwise Event Coreference Model, Feature Impact and Evaluation for Event Coreference Resolution

Zheng Chen, Heng Ji, Robert Haralick

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

Abstract

In past years, there has been substantial work on the problem of entity coreference resolution whereas much less attention has been paid to event coreference resolution. Starting with some motivating examples, we formally state the problem of event coreference resolution in the ACE 1 program, present an agglomerative clustering algorithm for the task, explore the feature impact in the event coreference model and compare three evaluation metrics that were previously adopted in entity coreference resolution: MUC F-Measure, B-Cubed F-Measure and ECM F-Measure.

Original languageEnglish (US)
Title of host publicationInternational Workshop on Events in Emerging Text Types, eETTs 2009 - held in conjunction with the International Conference RANLP 2009, Proceedings
EditorsConstantin Orasan, Laura Hasler, Corina Forascu
PublisherAssociation for Computational Linguistics (ACL)
Pages17-22
Number of pages6
ISBN (Electronic)9789544520113
StatePublished - 2009
Externally publishedYes
Event2009 International Workshop on Events in Emerging Text Types, eETTs 2009 - held in conjunction with the International Conference RANLP 2009 - Borovets, Bulgaria
Duration: Sep 17 2009 → …

Publication series

NameInternational Workshop on Events in Emerging Text Types, eETTs 2009 - held in conjunction with the International Conference RANLP 2009, Proceedings

Conference

Conference2009 International Workshop on Events in Emerging Text Types, eETTs 2009 - held in conjunction with the International Conference RANLP 2009
Country/TerritoryBulgaria
CityBorovets
Period9/17/09 → …

Keywords

  • Event Attribute
  • Event Coreference Resolution
  • Pairwise Event Coreference Model

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Software
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'A Pairwise Event Coreference Model, Feature Impact and Evaluation for Event Coreference Resolution'. Together they form a unique fingerprint.

Cite this