Document-Level Event Argument Extraction by Leveraging Redundant Information and Closed Boundary Loss

Hanzhang Zhou, Kezhi Mao


Abstract
In document-level event argument extraction, an argument is likely to appear multiple times in different expressions in the document. The redundancy of arguments underlying multiple sentences is beneficial but is often overlooked. In addition, in event argument extraction, most entities are regarded as class “others”, i.e. Universum class, which is defined as a collection of samples that do not belong to any class of interest. Universum class is composed of heterogeneous entities without typical common features. Classifiers trained by cross entropy loss could easily misclassify the Universum class because of their open decision boundary. In this paper, to make use of redundant event information underlying a document, we build an entity coreference graph with the graph2token module to produce a comprehensive and coreference-aware representation for every entity and then build an entity summary graph to merge the multiple extraction results. To better classify Universum class, we propose a new loss function to build classifiers with closed boundaries. Experimental results show that our model outperforms the previous state-of-the-art models by 3.35% in F1-score.
Anthology ID:
2022.naacl-main.222
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3041–3052
Language:
URL:
https://aclanthology.org/2022.naacl-main.222
DOI:
10.18653/v1/2022.naacl-main.222
Bibkey:
Cite (ACL):
Hanzhang Zhou and Kezhi Mao. 2022. Document-Level Event Argument Extraction by Leveraging Redundant Information and Closed Boundary Loss. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3041–3052, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Document-Level Event Argument Extraction by Leveraging Redundant Information and Closed Boundary Loss (Zhou & Mao, NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.222.pdf