Alson at NADI 2024 shared task: Alson - A fine-tuned model for Arabic Dialect Translation

Manan AlMusallam, Samar Ahmad


Abstract
DA-MSA Machine Translation is a recentchallenge due to the multitude of Arabic dialects and their variations. In this paper, we present our results within the context of Subtask 3 of the NADI-2024 Shared Task(Abdul-Mageed et al., 2024) that is DA-MSA Machine Translation . We utilized the DIALECTS008MSA MADAR corpus (Bouamor et al., 2018),the Emi-NADI corpus for the Emirati dialect (Khered et al., 2023), and we augmented thePalestinian and Jordanian datasets based onNADI 2021. Our approach involves develop013ing sentence-level machine translations fromPalestinian, Jordanian, Emirati, and Egyptiandialects to Modern Standard Arabic (MSA).To016 address this challenge, we fine-tuned models such as (Nagoudi et al., 2022)AraT5v2-msa-small, AraT5v2-msa-base, and (Elmadanyet al., 2023)AraT5v2-base-1024 to comparetheir performance. Among these, the AraT5v2-base-1024 model achieved the best accuracy, with a BLEU score of 0.1650 on the develop023ment set and 0.1746 on the test set.
Anthology ID:
2024.arabicnlp-1.86
Volume:
Proceedings of The Second Arabic Natural Language Processing Conference
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Nizar Habash, Houda Bouamor, Ramy Eskander, Nadi Tomeh, Ibrahim Abu Farha, Ahmed Abdelali, Samia Touileb, Injy Hamed, Yaser Onaizan, Bashar Alhafni, Wissam Antoun, Salam Khalifa, Hatem Haddad, Imed Zitouni, Badr AlKhamissi, Rawan Almatham, Khalil Mrini
Venues:
ArabicNLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
764–768
Language:
URL:
https://aclanthology.org/2024.arabicnlp-1.86
DOI:
Bibkey:
Cite (ACL):
Manan AlMusallam and Samar Ahmad. 2024. Alson at NADI 2024 shared task: Alson - A fine-tuned model for Arabic Dialect Translation. In Proceedings of The Second Arabic Natural Language Processing Conference, pages 764–768, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Alson at NADI 2024 shared task: Alson - A fine-tuned model for Arabic Dialect Translation (AlMusallam & Ahmad, ArabicNLP-WS 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2024.arabicnlp-1.86.pdf