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

Add code
Jun 10, 2021
Léo Bouscarrat, Antoine Bonnefoy, Cécile Capponi, Carlos Ramisch
Figure 1 for AMU-EURANOVA at CASE 2021 Task 1: Assessing the stability of multilingual BERT
Figure 2 for AMU-EURANOVA at CASE 2021 Task 1: Assessing the stability of multilingual BERT
Figure 3 for AMU-EURANOVA at CASE 2021 Task 1: Assessing the stability of multilingual BERT
Figure 4 for AMU-EURANOVA at CASE 2021 Task 1: Assessing the stability of multilingual BERT

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

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.

* Proceedings of the 4th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE 2021), Aug 2021, Online, Unknown Region  
View paper onarxiv icon

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon