Frank at NADI 2023 Shared Task: Trio-Based Ensemble Approach for Arabic Dialect Identification

Dilshod Azizov, Jiyong Li, Shangsong Liang

Abstract
We present our system designed for Subtask 1 in the shared task NADI on Arabic Dialect Identification, which is part of ArabicNLP 2023. In our approach, we utilized models such as: MARBERT, MARBERTv2 (A) and MARBERTv2 (B). Subsequently, we created a majority voting ensemble of these models. We used MARBERTv2 with different hyperparameters, which significantly improved the overall performance of the ensemble model. In terms of performance, our systems achieved a competitive an F1 score of 84.76. Overall, our system secured the 5th position out of 16 participating teams.
Anthology ID:
2023.arabicnlp-1.67
Volume:
Proceedings of ArabicNLP 2023
Month:
December
Year:
2023
Address:
Singapore (Hybrid)
Editors:
Hassan Sawaf, Samhaa El-Beltagy, Wajdi Zaghouani, Walid Magdy, Ahmed Abdelali, Nadi Tomeh, Ibrahim Abu Farha, Nizar Habash, Salam Khalifa, Amr Keleg, Hatem Haddad, Imed Zitouni, Khalil Mrini, Rawan Almatham
Venues:
ArabicNLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
637–641
Language:
URL:
https://aclanthology.org/2023.arabicnlp-1.67
DOI:
10.18653/v1/2023.arabicnlp-1.67
Bibkey:
Cite (ACL):
Dilshod Azizov, Jiyong Li, and Shangsong Liang. 2023. Frank at NADI 2023 Shared Task: Trio-Based Ensemble Approach for Arabic Dialect Identification. In Proceedings of ArabicNLP 2023, pages 637–641, Singapore (Hybrid). Association for Computational Linguistics.
Cite (Informal):
Frank at NADI 2023 Shared Task: Trio-Based Ensemble Approach for Arabic Dialect Identification (Azizov et al., ArabicNLP-WS 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/improve-issue-templates/2023.arabicnlp-1.67.pdf
PDF Search