TY - JOUR
T1 - NLP-CIC at HASOC 2020
T2 - Working Notes of FIRE - 12th Forum for Information Retrieval Evaluation, FIRE-WN 2020
AU - Aroyehun, Segun Taofeek
AU - Gelbukh, Alexander
N1 - Publisher Copyright:
© 2020 Copyright for this paper by its authors.
PY - 2020
Y1 - 2020
N2 - We describe our deep learning model submitted to the HASOC 2020 shared task on detection of offensive language in social media in three Indo-European languages: English, German, and Hindi. We fine-tune a pre-trained multilingual encoder on the combination of data provided for the competition. Our submission received a competitive macro- average F1 score of 0.4980 on the English Subtask A as well as comparatively strong performance on the German data.
AB - We describe our deep learning model submitted to the HASOC 2020 shared task on detection of offensive language in social media in three Indo-European languages: English, German, and Hindi. We fine-tune a pre-trained multilingual encoder on the combination of data provided for the competition. Our submission received a competitive macro- average F1 score of 0.4980 on the English Subtask A as well as comparatively strong performance on the German data.
KW - Deep learning
KW - Multilingual
KW - Offensive content identification
KW - Text classification
UR - http://www.scopus.com/inward/record.url?scp=85102960037&partnerID=8YFLogxK
M3 - Artículo de la conferencia
AN - SCOPUS:85102960037
SN - 1613-0073
VL - 2826
SP - 331
EP - 335
JO - CEUR Workshop Proceedings
JF - CEUR Workshop Proceedings
Y2 - 16 December 2020 through 20 December 2020
ER -