@inproceedings{fares-2024-arat5,
title = "{A}ra{T}5-{MSA}izer: Translating Dialectal {A}rabic to {MSA}",
author = "Fares, Murhaf",
editor = "Al-Khalifa, Hend and
Darwish, Kareem and
Mubarak, Hamdy and
Ali, Mona and
Elsayed, Tamer",
booktitle = "Proceedings of the 6th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT) with Shared Tasks on Arabic LLMs Hallucination and Dialect to MSA Machine Translation @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.osact-1.16/",
pages = "124--129",
abstract = "This paper outlines the process of training the AraT5-MSAizer model, a transformer-based neural machine translation model aimed at translating five regional Arabic dialects into Modern Standard Arabic (MSA). Developed for Task 2 of the 6th Workshop on Open-Source Arabic Corpora and Processing Tools, the model attained a BLEU score of 21.79{\%} on the test set associated with this task."
}
Markdown (Informal)
[AraT5-MSAizer: Translating Dialectal Arabic to MSA](https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.osact-1.16/) (Fares, OSACT 2024)
ACL
- Murhaf Fares. 2024. AraT5-MSAizer: Translating Dialectal Arabic to MSA. In Proceedings of the 6th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT) with Shared Tasks on Arabic LLMs Hallucination and Dialect to MSA Machine Translation @ LREC-COLING 2024, pages 124–129, Torino, Italia. ELRA and ICCL.