AMU-EURANOVA at CASE 2021 Task 1: Assessing the stability of multilingual BERT

Léo Bouscarrat, Antoine Bonnefoy, Cécile Capponi, Carlos Ramisch


Abstract
This paper explains our participation in task 1 of the CASE 2021 shared task. This task is about multilingual event extraction from news. We focused on sub-task 4, event information extraction. This sub-task has a small training dataset and we fine-tuned a multilingual BERT to solve this sub-task. We studied the instability problem on the dataset and tried to mitigate it.
Anthology ID:
2021.case-1.21
Volume:
Proceedings of the 4th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE 2021)
Month:
August
Year:
2021
Address:
Online
Editor:
Ali Hürriyetoğlu
Venue:
CASE
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
161–170
Language:
URL:
https://aclanthology.org/2021.case-1.21
DOI:
10.18653/v1/2021.case-1.21
Bibkey:
Cite (ACL):
Léo Bouscarrat, Antoine Bonnefoy, Cécile Capponi, and Carlos Ramisch. 2021. AMU-EURANOVA at CASE 2021 Task 1: Assessing the stability of multilingual BERT. In Proceedings of the 4th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE 2021), pages 161–170, Online. Association for Computational Linguistics.
Cite (Informal):
AMU-EURANOVA at CASE 2021 Task 1: Assessing the stability of multilingual BERT (Bouscarrat et al., CASE 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.case-1.21.pdf
Code
 euranova/AMU-EURANOVA-CASE-2021
Data
CoNLL 2002CoNLL 2003