Fakhraddin Alwajih, Abdellah El Mekki, Samar Mohamed Magdy, AbdelRahim A. Elmadany, Omer Nacar, El Moatez Billah Nagoudi, Reem Abdel-Salam, Hanin Atwany, Youssef Nafea, Abdulfattah Mohammed Yahya, Rahaf Alhamouri, Hamzah A. Alsayadi, Hiba Zayed, Sara Shatnawi, Serry Sibaee, Yasir Ech-chammakhy, Walid Al-Dhabyani, Marwa Mohamed Ali, Imen Jarraya, Ahmed Oumar El-Shangiti, Aisha Alraeesi, Mohammed Anwar AL-Ghrawi, Abdulrahman S. Al-Batati, Elgizouli Mohamed, Noha Taha Elgindi, Muhammed Saeed, Houdaifa Atou, Issam Ait Yahia, Abdelhak Bouayad, Mohammed Machrouh, Amal Makouar, Dania Alkawi, Mukhtar Mohamed, Safaa Taher Abdelfadil, Amine Ziad Ounnoughene, Anfel Rouabhia, Rwaa Assi, Ahmed Sorkatti, Mohamedou Cheikh Tourad, Anis Koubaa, Ismail Berrada, Mustafa Jarrar, Shady Shehata, Muhammad Abdul-Mageed. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Fakhraddin Alwajih, El Moatez Billah Nagoudi, Gagan Bhatia, Abdelrahman Mohamed, Muhammad Abdul-Mageed. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Bashar Talafha, Karima Kadaoui, Samar Mohamed Magdy, Mariem Habiboullah, Chafei Mohamed Chafei, Ahmed Oumar El-Shangiti, Hiba Zayed, Mohamedou Cheikh Tourad, Rahaf Alhamouri, Rwaa Assi, Aisha Alraeesi, Hour Mohamed, Fakhraddin Alwajih, Abdelrahman Mohamed, Abdellah El Mekki, El Moatez Billah Nagoudi, Benelhadj Djelloul Mama Saadia, Hamzah A. Alsayadi, Walid Al-Dhabyani, Sara Shatnawi, Yasir Ech-chammakhy, Amal Makouar, Yousra Berrachedi, Mustafa Jarrar, Shady Shehata, Ismail Berrada, Muhammad Abdul-Mageed. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

ChatGPT's emergence heralds a transformative phase in NLP, particularly demonstrated through its excellent performance on many English benchmarks.However, the model's efficacy across diverse linguistic contexts remains largely uncharted territory.This work aims to bridge this knowledge gap, with a primary focus on assessing ChatGPT's capabilities on Arabic languages and dialectal varieties.Our comprehensive study conducts a largescale automated and human evaluation of ChatGPT, encompassing 44 distinct language understanding and generation tasks on over 60 different datasets.To our knowledge, this marks the first extensive performance analysis of ChatGPT's deployment in Arabic NLP.Our findings indicate that, despite its remarkable performance in English, ChatGPT is consistently surpassed by smaller models that have undergone finetuning on Arabic.We further undertake a meticulous comparison of ChatGPT and GPT-4's Modern Standard Arabic (MSA) and Dialectal Arabic (DA), unveiling the relative shortcomings of both models in handling Arabic dialects compared to MSA.Although we further explore and confirm the utility of employing GPT-4 as a potential alternative for human evaluation, our work adds to a growing body of research underscoring the limitations of ChatGPT.

El Moatez Billah Nagoudi, Muhammad Abdul-Mageed, AbdelRahim Elmadany, Alcides Inciarte, Md Tawkat Islam Khondaker. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

Abdellah El Mekki, Muhammad Abdul-Mageed, ElMoatez Billah Nagoudi, Ismail Berrada, Ahmed Khoumsi. Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Transfer learning with a unified Transformer framework (T5) that converts all language problems into a text-to-text format was recently proposed as a simple and effective transfer learning approach.Although a multilingual version of the T5 model (mT5) was also introduced, it is not clear how well it can fare on non-English tasks involving diverse data.To investigate this question, we apply mT5 on a language with a wide variety of dialects-Arabic.For evaluation, we introduce a novel benchmark for ARabic language GENeration (ARGEN), covering seven important tasks.For model comparison, we pre-train three powerful Arabic T5-style models and evaluate them on ARGEN.Although pre-trained with ∼ 49% less data, our new models perform significantly better than mT5 on all ARGEN tasks (in 52 out of 59 test sets) and set several new SOTAs.Our models also establish new SOTA on the recently-proposed, large Arabic language understanding evaluation benchmark ARLUE (Abdul-Mageed et al., 2021).Our models are publicly available.We also link to individual ARGEN datasets through our public repository. 1

Muhammad Abdul-Mageed, AbdelRahim Elmadany, El Moatez Billah Nagoudi. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Muhammad Abdul-Mageed, AbdelRahim Elmadany, El Moatez Billah Nagoudi, Dinesh Pabbi, Kunal Verma, Rannie Lin. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. 2021.

Text search is the basis of countless applications and techniques. It is constrained by space and time resource limitations inherent in different contexts and scenarios. A common approach to minimize the cost of the general search task is to start by the characteristics which are particular to the targeted entity. In this paper, we propose an approximative index-based text searching algorithm that performances can be customized respect to both time/memory user constraints. The main idea is to exploit the uneven distribution of frequencies of letters and n-grams in natural language text, to reduce the index size and the search time, where we store only the less frequent letters and n-grams. Moreover, our technique can also provide to the user the flexibility to choose the tradeoff between index size and query performance. Search time and the index size can be balanced by varying three parameters in our approach. This makes our approach flexible to different settings. The tests described in this paper are driven on an Arabic collection of more than 450 documents and more than 20 million words. Experimental results show that the size of our n-gram inverted index is reduced by up to 40%–85% (with tolerable performance penalties) compared with those of the full n-gram inverted index. Generalization to other languages should be straightforward as long as the underlying statistical property applies.