Joint Modeling of Arguments for Event Understanding

Yunmo Chen, Tongfei Chen, Benjamin Van Durme


Abstract
We recognize the task of event argument linking in documents as similar to that of intent slot resolution in dialogue, providing a Transformer-based model that extends from a recently proposed solution to resolve references to slots. The approach allows for joint consideration of argument candidates given a detected event, which we illustrate leads to state-of-the-art performance in multi-sentence argument linking.
Anthology ID:
2020.codi-1.10
Volume:
Proceedings of the First Workshop on Computational Approaches to Discourse
Month:
November
Year:
2020
Address:
Online
Editors:
Chloé Braud, Christian Hardmeier, Junyi Jessy Li, Annie Louis, Michael Strube
Venue:
CODI
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
96–101
Language:
URL:
https://aclanthology.org/2020.codi-1.10
DOI:
10.18653/v1/2020.codi-1.10
Bibkey:
Cite (ACL):
Yunmo Chen, Tongfei Chen, and Benjamin Van Durme. 2020. Joint Modeling of Arguments for Event Understanding. In Proceedings of the First Workshop on Computational Approaches to Discourse, pages 96–101, Online. Association for Computational Linguistics.
Cite (Informal):
Joint Modeling of Arguments for Event Understanding (Chen et al., CODI 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.codi-1.10.pdf
Video:
 https://slideslive.com/38939698