ANLP-RG at NADI 2023 shared task: Machine Translation of Arabic Dialects: A Comparative Study of Transformer Models

Wiem Derouich, Sameh Kchaou, Rahma Boujelbane


Abstract
In this paper, we present our findings within the context of the NADI-2023 Shared Task (Subtask 2). Our task involves developing a translation model from the Palestinian, Jordanian, Emirati, and Egyptian dialects to Modern Standard Arabic (MSA) using the MADAR parallel corpus, even though it lacks a parallel subset for the Emirati dialect. To address this challenge, we conducted a comparative analysis, evaluating the fine-tuning results of various transformer models using the MADAR corpus as a learning resource. Additionally, we assessed the effectiveness of existing translation tools in achieving our translation objectives. The best model achieved a BLEU score of 11.14% on the dev set and 10.02 on the test set.
Anthology ID:
2023.arabicnlp-1.75
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:
683–689
Language:
URL:
https://aclanthology.org/2023.arabicnlp-1.75
DOI:
10.18653/v1/2023.arabicnlp-1.75
Bibkey:
Cite (ACL):
Wiem Derouich, Sameh Kchaou, and Rahma Boujelbane. 2023. ANLP-RG at NADI 2023 shared task: Machine Translation of Arabic Dialects: A Comparative Study of Transformer Models. In Proceedings of ArabicNLP 2023, pages 683–689, Singapore (Hybrid). Association for Computational Linguistics.
Cite (Informal):
ANLP-RG at NADI 2023 shared task: Machine Translation of Arabic Dialects: A Comparative Study of Transformer Models (Derouich et al., ArabicNLP-WS 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-2024-clasp/2023.arabicnlp-1.75.pdf
Video:
 https://preview.aclanthology.org/ingest-2024-clasp/2023.arabicnlp-1.75.mp4