Span-Based Event Coreference Resolution

AAAI 2021 pp. 13489-13497

doi:10.1609/AAAI.V35I15.17591 /aaai/2021/lu2021aaai-span/

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 span-based 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.

PDF AAAI Semantic Scholar

Cite

Text

Lu and Ng. "Span-Based Event Coreference Resolution." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I15.17591

Markdown

[Lu and Ng. "Span-Based Event Coreference Resolution." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/lu2021aaai-span/) doi:10.1609/AAAI.V35I15.17591

BibTeX

@inproceedings{lu2021aaai-span,
  title     = {{Span-Based Event Coreference Resolution}},
  author    = {Lu, Jing and Ng, Vincent},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2021},
  pages     = {13489-13497},
  doi       = {10.1609/AAAI.V35I15.17591},
  url       = {https://mlanthology.org/aaai/2021/lu2021aaai-span/}
}