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

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.

Domaines

Intelligence artificielle [cs.AI] Informatique et langage [cs.CL]

Fichier principal

Shared_task_CASE_2021_bouscarrat.pdf (631.54 Ko)

Origine	Fichiers produits par l'(les) auteur(s)

Léo Bouscarrat : Connectez-vous pour contacter le contributeur

https://hal.science/hal-03255722

Soumis le : mercredi 9 juin 2021-17:28:37

Dernière modification le : lundi 10 juin 2024-16:50:19

Archivage à long terme le : vendredi 10 septembre 2021-19:13:41

Dates et versions

hal-03255722 , version 1 (09-06-2021)

hal-03255722 , version 2 (16-07-2021)

Identifiants

HAL Id : hal-03255722 , version 1
ARXIV : 2106.14625

Citer

Léo Bouscarrat, Antoine Bonnefoy, Cécile Capponi, Carlos Ramisch. AMU-EURANOVA at CASE 2021 Task 1: Assessing the stability of multilingual BERT. 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. ⟨hal-03255722v1⟩

Exporter

BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite

123 Consultations

89 Téléchargements