Skip to content
conftrace_
2021 ACL ACL 2021

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

Abstract

AbstractThis 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.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Léo Bouscarrat, Antoine Bonnefoy, Cécile Capponi, Carlos Ramisch

Topics

Deep Learning > Architectures > Transformers Natural Language Processing > Applications > Information Extraction Natural Language Processing > Resources & Methods > Multilingual NLP Deep Learning > Learning Types > Fine-Tuning

Keywords

stability analysis small dataset event extraction multilingual bert
Download PDF

More from ACL 2021

All ACL 2021 papers →
IBM MNLP IE at CASE 2021 Task 1: Multigranular and Multilingual Event Detection on Protest News
ALEM at CASE 2021 Task 1: Multilingual Text Classification on News Articles
Team “NoConflict” at CASE 2021 Task 1: Pretraining for Sentence-Level Protest Event Detection
Team “DaDeFrNi” at CASE 2021 Task 1: Document and Sentence Classification for Protest Event Detection
Fine-grained Event Classification in News-like Text Snippets - Shared Task 2, CASE 2021
IBM MNLP IE at CASE 2021 Task 2: NLI Reranking for Zero-Shot Text Classification