Unleash GPT-2 Power for Event Detection

Amir Pouran Ben Veyseh, Viet Lai, Franck Dernoncourt, Thien Huu Nguyen


Abstract
Event Detection (ED) aims to recognize mentions of events (i.e., event triggers) and their types in text. Recently, several ED datasets in various domains have been proposed. However, the major limitation of these resources is the lack of enough training data for individual event types which hinders the efficient training of data-hungry deep learning models. To overcome this issue, we propose to exploit the powerful pre-trained language model GPT-2 to generate training samples for ED. To prevent the noises inevitable in automatically generated data from hampering training process, we propose to exploit a teacher-student architecture in which the teacher is supposed to learn anchor knowledge from the original data. The student is then trained on combination of the original and GPT-generated data while being led by the anchor knowledge from the teacher. Optimal transport is introduced to facilitate the anchor knowledge-based guidance between the two networks. We evaluate the proposed model on multiple ED benchmark datasets, gaining consistent improvement and establishing state-of-the-art results for ED.
Anthology ID:
2021.acl-long.490
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6271–6282
Language:
URL:
https://aclanthology.org/2021.acl-long.490
DOI:
10.18653/v1/2021.acl-long.490
Bibkey:
Cite (ACL):
Amir Pouran Ben Veyseh, Viet Lai, Franck Dernoncourt, and Thien Huu Nguyen. 2021. Unleash GPT-2 Power for Event Detection. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 6271–6282, Online. Association for Computational Linguistics.
Cite (Informal):
Unleash GPT-2 Power for Event Detection (Pouran Ben Veyseh et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/2021.acl-long.490.pdf
Video:
 https://preview.aclanthology.org/landing_page/2021.acl-long.490.mp4