TY - GEN
T1 - Graph-based event coreference resolution
AU - Chen, Zheng
AU - Ji, Heng
PY - 2009
Y1 - 2009
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=84883295435&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84883295435&partnerID=8YFLogxK
U2 - 10.3115/1708124.1708135
DO - 10.3115/1708124.1708135
M3 - Conference contribution
AN - SCOPUS:84883295435
SN - 193243254X
SN - 9781932432541
T3 - ACL-IJCNLP 2009 - TextGraphs 2009: 2009 Workshop on Graph-Based Methods for Natural Language Processing, Proceedings of the Workshop
SP - 54
EP - 57
BT - ACL-IJCNLP 2009 - TextGraphs 2009
PB - Association for Computational Linguistics (ACL)
T2 - 4th Workshop on Graph-Based Methods for Natural Language Processing, TextGraphs 2009
Y2 - 7 August 2009 through 7 August 2009
ER -