CUFE at NADI 2024 shared task: Fine-Tuning Llama-3 To Translate From Arabic Dialects To Modern Standard Arabic
Domain:
natural language processingRecord type:
paper
Creator:
AssIbr
Publisher:
Und
Host:
LLMs such as GPT-4 and LLaMA excel in multiple natural language processing tasks, however, LLMs face challenges in delivering satisfactory performance on low-resource languages due to limited availability of training data. In this paper, LLaMA-3 with 8 Billion parameters is finetuned to translate among Egyptian, Emirati, Jordanian, Palestinian Arabic dialects, and Modern Standard Arabic (MSA). In the NADI 2024 Task on DA-MSA Machine Translation, the proposed method achieved a BLEU score of 21.44 when it was fine-tuned on the development dataset of the NADI 2024 Task on DA-MSA and a BLEU score of 16.09 when trained when it was fine-tuned using the OSACT dataset.
Similar
Munsit at NADI 2025 Shared Task 2: Pushing the Boundaries of Multidialectal Arabic ASR with Weakly Supervised Pretraining and Continual Supervised Fine-tuningNADI 2025: The First Multidialectal Arabic Speech Processing Shared TaskSpeech Translation From Darija to Modern Standard Arabic: Fine-Tuning Whisper on the Darija-C Corpus Across Six Model VersionsAdvancing Dialectal Arabic to Modern Standard Arabic Machine TranslationAHaSIS: Shared Task on Sentiment Analysis for Arabic DialectsTranslation system from Tunisian Dialect to Modern Standard Arabic