Abstract
Motivated by the recent successful application of span-based models to entity-based information extraction tasks, we investigate span-based models for event coreference resolution, focusing on determining (1) whether the successes of spanbased models of entity coreference can be extended to event coreference; (2) whether exploiting the dependency between event coreference and the related subtask of trigger detection; and (3) whether automatically computed entity coreference information can benefit span-based event coreference resolution. Empirical results on the standard evaluation dataset provide affirmative answers to all three questions.
Cite
CITATION STYLE
Lu, J., & Ng, V. (2021). Span-Based Event Coreference Resolution. In 35th AAAI Conference on Artificial Intelligence, AAAI 2021 (Vol. 15, pp. 13489–13497). Association for the Advancement of Artificial Intelligence. https://doi.org/10.1609/aaai.v35i15.17591
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.