iCompass at Shared Task on Sarcasm and Sentiment Detection in Arabic

Malek Naski, Abir Messaoudi, Hatem Haddad, Moez BenHajhmida, Chayma Fourati, Aymen Ben Elhaj Mabrouk


Abstract
We describe our submitted system to the 2021 Shared Task on Sarcasm and Sentiment Detection in Arabic (Abu Farha et al., 2021). We tackled both subtasks, namely Sarcasm Detection (Subtask 1) and Sentiment Analysis (Subtask 2). We used state-of-the-art pretrained contextualized text representation models and fine-tuned them according to the downstream task in hand. As a first approach, we used Google’s multilingual BERT and then other Arabic variants: AraBERT, ARBERT and MARBERT. The results found show that MARBERT outperforms all of the previously mentioned models overall, either on Subtask 1 or Subtask 2.
Anthology ID:
2021.wanlp-1.50
Volume:
Proceedings of the Sixth Arabic Natural Language Processing Workshop
Month:
April
Year:
2021
Address:
Kyiv, Ukraine (Virtual)
Editors:
Nizar Habash, Houda Bouamor, Hazem Hajj, Walid Magdy, Wajdi Zaghouani, Fethi Bougares, Nadi Tomeh, Ibrahim Abu Farha, Samia Touileb
Venue:
WANLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
381–385
Language:
URL:
https://aclanthology.org/2021.wanlp-1.50
DOI:
Bibkey:
Cite (ACL):
Malek Naski, Abir Messaoudi, Hatem Haddad, Moez BenHajhmida, Chayma Fourati, and Aymen Ben Elhaj Mabrouk. 2021. iCompass at Shared Task on Sarcasm and Sentiment Detection in Arabic. In Proceedings of the Sixth Arabic Natural Language Processing Workshop, pages 381–385, Kyiv, Ukraine (Virtual). Association for Computational Linguistics.
Cite (Informal):
iCompass at Shared Task on Sarcasm and Sentiment Detection in Arabic (Naski et al., WANLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.wanlp-1.50.pdf
Data
ArSarcasm-v2