Título |
Evaluation of intermediate pre-training for the detection of offensive language |
Tipo |
Congreso |
Sub-tipo |
Memoria |
Descripción |
2021 Iberian Languages Evaluation Forum, IberLEF 2021 |
Resumen |
This paper presents an evaluation of intermediate pre- training for the task of offensive language identification. We leverage recent advances in multilingual contextual representation and fine-tuning of pre-trained language models. We compare the performance of a pre- trained language model adapted for the social media domain and an- other that was further trained on multilingual sentiment analysis data. We found that the intermediate pre-training steps prior to fine-tuning on the target task yield performance gains. The best submissions by our team, NLP-CIC, achieved first and second place on the non-contextual Spanish (Subtask 1) and Mexican Spanish (Subtask 3) subtasks of the MeOffendEs-IberLEF 2021 shared task respectively. |
Observaciones |
CEUR Workshop Proceedings |
Lugar |
Virtual, online |
País |
España |
No. de páginas |
313-320 |
Vol. / Cap. |
v. 2943 |
Inicio |
2021-09-21 |
Fin |
|
ISBN/ISSN |
|