Explicit Role Interaction Network for Event Argument Extraction

Nan Ding, Chunming Hu, Kai Sun, Samuel Mensah, Richong Zhang


Abstract
Event argument extraction is a challenging subtask of event extraction, aiming to identify and assign roles to arguments under a certain event. Existing methods extract arguments of each role independently, ignoring the relationship between different roles. Such an approach hinders the model from learning explicit interactions between different roles to improve the performance of individual argument extraction. As a solution, we design a neural model that we refer to as the Explicit Role Interaction Network (ERIN) which allows for dynamically capturing the correlations between different argument roles within an event. Extensive experiments on the benchmark dataset ACE2005 demonstrate the superiority of our proposed model to existing approaches.
Anthology ID:
2022.findings-emnlp.254
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3475–3485
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.254
DOI:
Bibkey:
Cite (ACL):
Nan Ding, Chunming Hu, Kai Sun, Samuel Mensah, and Richong Zhang. 2022. Explicit Role Interaction Network for Event Argument Extraction. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 3475–3485, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Explicit Role Interaction Network for Event Argument Extraction (Ding et al., Findings 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2022.findings-emnlp.254.pdf