ABSTRACT
In this paper, we address the problem of event coreference resolution as specified in the Automatic Content Extraction (ACE) program. 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.
- A. Bagga and B. Baldwin. 1999. Cross-document event coreference: Annotations, experiments, and observations. In Proc. ACL-99 Workshop on Coreference and Its Applications. Google ScholarDigital Library
- C. Nicolae and G. Nicolae. 2006. Bestcut: A graph algorithm for coreference resolution. In EMNLP, pages 275--283, Sydney, Australia, July. Google ScholarDigital Library
- J. Shi and J. Malik. 1997. Normalized Cuts and Image Segmentation. In Proc. of IEEE Conf. on Comp. Vision and Pattern Recognition, Puerto Rico Google ScholarDigital Library
- K. Humphreys, R. Gaizauskas, S. Azzam. 1997. Event coreference for information extraction. In Proceedings of the ACL Workshop on Operational Factors in Practical Robust Anaphora Resolution for Unrestricted Texts. Google ScholarDigital Library
- N. Seco, T. Veale, J. Hayes. 2004. An intrinsic information content metric for semantic similarity in WordNet. In Proc. of ECAI-04, pp. 1089--1090.Google Scholar
- X. Luo. 2005. On coreference resolution performance metrics. Proc. of HLT-EMNLP. Google ScholarDigital Library
Index Terms
- Graph-based event coreference resolution
Recommendations
A pairwise event coreference model, feature impact and evaluation for event coreference resolution
eETTs '09: Proceedings of the Workshop on Events in Emerging Text TypesIn 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 ...
Joint entity and event coreference resolution across documents
EMNLP-CoNLL '12: Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language LearningWe introduce a novel coreference resolution system that models entities and events jointly. Our iterative method cautiously constructs clusters of entity and event mentions using linear regression to model cluster merge operations. As clusters are built,...
Comments