Generating Uncontextualized and Contextualized Questions for Document-Level Event Argument Extraction

Md Nayem Uddin, Enfa George, Eduardo Blanco, Steven Corman


Abstract
This paper presents multiple question generation strategies for document-level event argument extraction. These strategies do not require human involvement and result in uncontextualized questions as well as contextualized questions grounded on the event and document of interest. Experimental results show that combining uncontextualized and contextualized questions is beneficial,especially when event triggers and arguments appear in different sentences. Our approach does not have corpus-specific components, in particular, the question generation strategies transfer across corpora. We also present a qualitative analysis of the most common errors made by our best model.
Anthology ID:
2024.naacl-long.312
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5612–5627
Language:
URL:
https://aclanthology.org/2024.naacl-long.312
DOI:
Bibkey:
Cite (ACL):
Md Nayem Uddin, Enfa George, Eduardo Blanco, and Steven Corman. 2024. Generating Uncontextualized and Contextualized Questions for Document-Level Event Argument Extraction. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 5612–5627, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Generating Uncontextualized and Contextualized Questions for Document-Level Event Argument Extraction (Uddin et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-long.312.pdf
Copyright:
 2024.naacl-long.312.copyright.pdf