What Is Overlap Knowledge in Event Argument Extraction? APE: A Cross-datasets Transfer Learning Model for EAE

Kaihang Zhang, Kai Shuang, Xinyue Yang, Xuyang Yao, Jinyu Guo


Abstract
The EAE task extracts a structured event record from an event text. Most existing approaches train the EAE model on each dataset independently and ignore the overlap knowledge across datasets. However, insufficient event records in a single dataset often prevent the existing model from achieving better performance. In this paper, we clearly define the overlap knowledge across datasets and split the knowledge of the EAE task into overlap knowledge across datasets and specific knowledge of the target dataset. We propose APE model to learn the two parts of knowledge in two serial learning phases without causing catastrophic forgetting. In addition, we formulate both learning phases as conditional generation tasks and design Stressing Entity Type Prompt to close the gap between the two phases. The experiments show APE achieves new state-of-the-art with a large margin in the EAE task. When only ten records are available in the target dataset, our model dramatically outperforms the baseline model with average 27.27% F1 gain.
Anthology ID:
2023.acl-long.24
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
393–409
Language:
URL:
https://aclanthology.org/2023.acl-long.24
DOI:
10.18653/v1/2023.acl-long.24
Bibkey:
Cite (ACL):
Kaihang Zhang, Kai Shuang, Xinyue Yang, Xuyang Yao, and Jinyu Guo. 2023. What Is Overlap Knowledge in Event Argument Extraction? APE: A Cross-datasets Transfer Learning Model for EAE. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 393–409, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
What Is Overlap Knowledge in Event Argument Extraction? APE: A Cross-datasets Transfer Learning Model for EAE (Zhang et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.24.pdf
Video:
 https://aclanthology.org/2023.acl-long.24.mp4