IRIT-PREVISION AT HASOC 2020 : Fine-tuning BERT for Hate Speech and Offensive Content Identification - Systèmes d’Informations Généralisées Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

IRIT-PREVISION AT HASOC 2020 : Fine-tuning BERT for Hate Speech and Offensive Content Identification

Résumé

This paper describes the participation of the IRIT-PREVISION team at HASOC (Hate Speech and Offensive Content Identification in Indo-European Languages) 2020 shared task. Our approach is based on fine-tuning a pre-trained transformer based language model BERT (Bidirectional Encoder Representation from Transformer) [1]. We participated to the English sub-task A. We obtained a macro average F1 of 0.497 (self-computed).
Fichier principal
Vignette du fichier
2020_HASOC-FIRE_MPF.pdf (321.8 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03040547 , version 1 (04-12-2020)
hal-03040547 , version 2 (20-01-2021)

Identifiants

  • HAL Id : hal-03040547 , version 1

Citer

Josiane Mothe, Pratik Parikh, Faneva Ramiandrisoa. IRIT-PREVISION AT HASOC 2020 : Fine-tuning BERT for Hate Speech and Offensive Content Identification. Hate Speech and Offensive Content Identification in Indo-European Languages (HASOC@FIRE 2020), Dec 2020, Hyderabad (virtual), India. ⟨hal-03040547v1⟩
197 Consultations
376 Téléchargements

Partager

Gmail Facebook X LinkedIn More