This paper explores Dialectal Arabic (DA) to Modern Standard Arabic (MSA) machine translation using prompting and fine-tuning techniques for Levantine, Egyptian, and Gulf dialects. The study found that few-shot prompting outperformed zero-shot and chain-of-thought methods across six large language models, with GPT-4o achieving the highest performance. A quantized Gemma2-9B model achieved a chrF++ score of 49.88, outperforming zero-shot GPT-4o (44.58). Why it matters: The research provides a resource-efficient pipeline for DA-MSA translation, enabling more inclusive language technologies by addressing the challenges posed by dialectal variations in Arabic.
The paper introduces ALLaM, a series of large language models for Arabic and English, designed to support Arabic Language Technologies. The models are trained with language alignment and knowledge transfer in mind, using a decoder-only architecture. ALLaM achieves state-of-the-art results on Arabic benchmarks like MMLU Arabic and Arabic Exams. Why it matters: This work advances Arabic NLP by providing high-performing LLMs and demonstrating effective techniques for cross-lingual transfer learning and alignment with human preferences.
Qatar is investing heavily in AI to reduce its reliance on foreign technology companies. The country aims to become a leader in AI research and development, with a focus on Arabic language technologies and applications relevant to the region. Qatar's efforts are driven by concerns about data security, privacy, and the potential for AI to drive economic diversification. Why it matters: This push for AI sovereignty reflects a broader trend in the Middle East, as countries seek to develop their own AI capabilities and reduce dependence on foreign providers.
This paper surveys the landscape of code-switched Arabic natural language processing, covering the mixture of Modern Standard Arabic, dialects, and foreign languages. It examines current efforts, challenges, and research gaps in the field. The survey also provides recommendations for future research directions in code-switched Arabic NLP. Why it matters: Understanding code-switching is crucial for developing effective language technologies that can handle the diverse linguistic landscape of the Arab world.
Qatar Computing Research Institute (QCRI) is undertaking cutting-edge AI research and development, including work on Arabic language technologies, computer vision, and data analytics. QCRI's projects span healthcare, disaster response, and cybersecurity. Why it matters: QCRI's work helps to build local AI expertise and address regional challenges.