Ismail Berrada

Abdelkader El Mahdaouy, Abdellah El Mekki, Kabil Essefar et al.

Sarcasm is a form of figurative language where the intended meaning of a sentence differs from its literal meaning. This poses a serious challenge to several Natural Language Processing (NLP) applications such as Sentiment Analysis, Opinion Mining, and Author Profiling. In this paper, we present our participating system to the intended sarcasm detection task in English and Arabic languages. Our system\footnote{The source code of our system is available at \url{https://github.com/AbdelkaderMH/iSarcasmEval}} consists of three deep learning-based models leveraging two existing pre-trained language models for Arabic and English. We have participated in all sub-tasks. Our official submissions achieve the best performance on sub-task A for Arabic language and rank second in sub-task B. For sub-task C, our system is ranked 7th and 11th on Arabic and English datasets, respectively.

Abdellah El Mekki, Muhammad Abdul-Mageed, ElMoatez Billah Nagoudi et al.

Bilingual Lexicon Induction (BLI), where words are translated between two languages, is an important NLP task. While noticeable progress on BLI in rich resource languages using static word embeddings has been achieved. The word translation performance can be further improved by incorporating information from contextualized word embeddings. In this paper, we introduce ProMap, a novel approach for BLI that leverages the power of prompting pretrained multilingual and multidialectal language models to address these challenges. To overcome the employment of subword tokens in these models, ProMap relies on an effective padded prompting of language models with a seed dictionary that achieves good performance when used independently. We also demonstrate the effectiveness of ProMap in re-ranking results from other BLI methods such as with aligned static word embeddings. When evaluated on both rich-resource and low-resource languages, ProMap consistently achieves state-of-the-art results. Furthermore, ProMap enables strong performance in few-shot scenarios (even with less than 10 training examples), making it a valuable tool for low-resource language translation. Overall, we believe our method offers both exciting and promising direction for BLI in general and low-resource languages in particular. ProMap code and data are available at \url{https://github.com/4mekki4/promap}.

Sanad Malaysha, Mo El-Haj, Saad Ezzini et al.

The expanding financial markets of the Arab world require sophisticated Arabic NLP tools. To address this need within the banking domain, the Arabic Financial NLP (AraFinNLP) shared task proposes two subtasks: (i) Multi-dialect Intent Detection and (ii) Cross-dialect Translation and Intent Preservation. This shared task uses the updated ArBanking77 dataset, which includes about 39k parallel queries in MSA and four dialects. Each query is labeled with one or more of a common 77 intents in the banking domain. These resources aim to foster the development of robust financial Arabic NLP, particularly in the areas of machine translation and banking chat-bots. A total of 45 unique teams registered for this shared task, with 11 of them actively participated in the test phase. Specifically, 11 teams participated in Subtask 1, while only 1 team participated in Subtask 2. The winning team of Subtask 1 achieved F1 score of 0.8773, and the only team submitted in Subtask 2 achieved a 1.667 BLEU score.

Abdelkader El Mahdaouy, Abdellah El Mekki, Ahmed Oumar et al.

The prevalence of toxic content on social media platforms, such as hate speech, offensive language, and misogyny, presents serious challenges to our interconnected society. These challenging issues have attracted widespread attention in Natural Language Processing (NLP) community. In this paper, we present the submitted systems to the first Arabic Misogyny Identification shared task. We investigate three multi-task learning models as well as their single-task counterparts. In order to encode the input text, our models rely on the pre-trained MARBERT language model. The overall obtained results show that all our submitted models have achieved the best performances (top three ranked submissions) in both misogyny identification and categorization tasks.

Abdellah El Mekki, Abdelkader El Mahdaouy, Mohammed Akallouch et al.

Building real-world complex Named Entity Recognition (NER) systems is a challenging task. This is due to the complexity and ambiguity of named entities that appear in various contexts such as short input sentences, emerging entities, and complex entities. Besides, real-world queries are mostly malformed, as they can be code-mixed or multilingual, among other scenarios. In this paper, we introduce our submitted system to the Multilingual Complex Named Entity Recognition (MultiCoNER) shared task. We approach the complex NER for multilingual and code-mixed queries, by relying on the contextualized representation provided by the multilingual Transformer XLM-RoBERTa. In addition to the CRF-based token classification layer, we incorporate a span classification loss to recognize named entities spans. Furthermore, we use a self-training mechanism to generate weakly-annotated data from a large unlabeled dataset. Our proposed system is ranked 6th and 8th in the multilingual and code-mixed MultiCoNER's tracks respectively.

Abdelkader El Mahdaouy, Salima Lamsiyah, Meryem Janati Idrissi et al.

Detecting and classifying suspicious or malicious domain names and URLs is fundamental task in cybersecurity. To leverage such indicators of compromise, cybersecurity vendors and practitioners often maintain and update blacklists of known malicious domains and URLs. However, blacklists frequently fail to identify emerging and obfuscated threats. Over the past few decades, there has been significant interest in developing machine learning models that automatically detect malicious domains and URLs, addressing the limitations of blacklists maintenance and updates. In this paper, we introduce DomURLs_BERT, a pre-trained BERT-based encoder adapted for detecting and classifying suspicious/malicious domains and URLs. DomURLs_BERT is pre-trained using the Masked Language Modeling (MLM) objective on a large multilingual corpus of URLs, domain names, and Domain Generation Algorithms (DGA) dataset. In order to assess the performance of DomURLs_BERT, we have conducted experiments on several binary and multi-class classification tasks involving domain names and URLs, covering phishing, malware, DGA, and DNS tunneling. The evaluations results show that the proposed encoder outperforms state-of-the-art character-based deep learning models and cybersecurity-focused BERT models across multiple tasks and datasets. The pre-training dataset, the pre-trained DomURLs_BERT encoder, and the experiments source code are publicly available.

Ismail Elbouknify, Afaf Bouhoute, Khalid Fardousse et al.

In this work, CT-xCOV, an explainable framework for COVID-19 diagnosis using Deep Learning (DL) on CT-scans is developed. CT-xCOV adopts an end-to-end approach from lung segmentation to COVID-19 detection and explanations of the detection model's prediction. For lung segmentation, we used the well-known U-Net model. For COVID-19 detection, we compared three different CNN architectures: a standard CNN, ResNet50, and DenseNet121. After the detection, visual and textual explanations are provided. For visual explanations, we applied three different XAI techniques, namely, Grad-Cam, Integrated Gradient (IG), and LIME. Textual explanations are added by computing the percentage of infection by lungs. To assess the performance of the used XAI techniques, we propose a ground-truth-based evaluation method, measuring the similarity between the visualization outputs and the ground-truth infections. The performed experiments show that the applied DL models achieved good results. The U-Net segmentation model achieved a high Dice coefficient (98%). The performance of our proposed classification model (standard CNN) was validated using 5-fold cross-validation (acc of 98.40% and f1-score 98.23%). Lastly, the results of the comparison of XAI techniques show that Grad-Cam gives the best explanations compared to LIME and IG, by achieving a Dice coefficient of 55%, on COVID-19 positive scans, compared to 29% and 24% obtained by IG and LIME respectively. The code and the dataset used in this paper are available in the GitHub repository [1].

Salmane Chafik, Saad Ezzini, Ismail Berrada

Recently, code-oriented large language models (LLMs) have demonstrated strong capabilities in translating natural language into executable code. Text-to-SQL is a significant application of this ability, enabling non-technical users to interact with relational databases using natural language. However, state-of-the-art models continue to struggle with highly complex logic, particularly deeply nested statements involving multiple joins and conditions, as well as with real-world database schemas that are noisy or poorly structured. In this paper, we investigate whether curriculum learning can improve the performance of code-based LLMs on Text-to-SQL tasks. Employing benchmarks including Spider and BIRD, we fine-tune models under different curriculum strategies. Our experiments show that naive curriculum, simply ordering training samples by complexity in a single epoch, fails to surpass standard fine-tuning due to catastrophic forgetting. To overcome this, we propose a Modular Adapter Composition (MAC) strategy. By sequentially training tier-specific adapters on incremental complexity levels (Easy to Extra-Hard), we create a scaffolded learning environment that improves performance on complex queries. Our approach not only produces measurable performance gains on the Spider and BIRD benchmarks but also provides a flexible, "Lego-like" architecture, allowing models to be composed and deployed based on specific schema difficulty requirements. These findings demonstrate that structured, modular learning is a superior alternative to monolithic fine-tuning for mastering the syntax and logic of complex code generation.

Fakhraddin Alwajih, Abdellah El Mekki, Samar Mohamed Magdy et al.

As large language models (LLMs) become increasingly integrated into daily life, ensuring their cultural sensitivity and inclusivity is paramount. We introduce our dataset, a year-long community-driven project covering all 22 Arab countries. The dataset includes instructions (input, response pairs) in both Modern Standard Arabic (MSA) and dialectal Arabic (DA), spanning 20 diverse topics. Built by a team of 44 researchers across the Arab world, all of whom are authors of this paper, our dataset offers a broad, inclusive perspective. We use our dataset to evaluate the cultural and dialectal capabilities of several frontier LLMs, revealing notable limitations. For instance, while closed-source LLMs generally exhibit strong performance, they are not without flaws, and smaller open-source models face greater challenges. Moreover, certain countries (e.g., Egypt, the UAE) appear better represented than others (e.g., Iraq, Mauritania, Yemen). Our annotation guidelines, code, and data for reproducibility are publicly available.

Abderrahman Skiredj, Ferdaous Azhari, Houdaifa Atou et al.

Open-source large language models (LLMs) still marginalise Moroccan Arabic (Darija), forcing practitioners either to bolt on heavyweight Arabic adapters or to sacrifice the very reasoning skills that make LLMs useful. We show that a rigorously quality-over-quantity alignment strategy can surface fluent Darija while safeguarding the backbone s cross-lingual reasoning at a sliver of the usual compute. We translate three compact instruction suites LIMA 1 K, DEITA 6 K and TULU 50 K into Darija, preserve 20 of the English originals, and add mathematics, coding and scientific prompts. A LoRA-tuned Gemma 3-4B trained on 5 K mixed instructions lifts DarijaMMLU from 32.8 to 42.7 ; adding the reasoning-dense TULU portion pushes it to 47.5 with no English regression. Scaling the identical recipe to Gemma 3-27B produces GemMaroc-27B, which matches Atlas-Chat on DarijaMMLU (61.6 ) and leaps ahead on Darija commonsense, scoring 60.5 on HellaSwag versus Atlas-Chat s 48.4 . Crucially, GemMaroc retains Gemma-27B s strong maths and general-reasoning ability, showing only minimal movement on GSM8K and English benchmarks. The entire model is trained in just 48 GPU.h, underscoring a Green AI pathway to inclusive, sustainable language technology. We release code, data and checkpoints to spur Darija-centric applications in education, public services and everyday digital interaction.

Abderrahman Skiredj, Ismail Berrada

Automatic diacritization of Arabic text involves adding diacritical marks (diacritics) to the text. This task poses a significant challenge with noteworthy implications for computational processing and comprehension. In this paper, we introduce PTCAD (Pre-FineTuned Token Classification for Arabic Diacritization, a novel two-phase approach for the Arabic Text Diacritization task. PTCAD comprises a pre-finetuning phase and a finetuning phase, treating Arabic Text Diacritization as a token classification task for pre-trained models. The effectiveness of PTCAD is demonstrated through evaluations on two benchmark datasets derived from the Tashkeela dataset, where it achieves state-of-the-art results, including a 20\% reduction in Word Error Rate (WER) compared to existing benchmarks and superior performance over GPT-4 in ATD tasks.

Fakhraddin Alwajih, Samar M. Magdy, Abdellah El Mekki et al.

Mainstream large vision-language models (LVLMs) inherently encode cultural biases, highlighting the need for diverse multimodal datasets. To address this gap, we introduce PEARL, a large-scale Arabic multimodal dataset and benchmark explicitly designed for cultural understanding. Constructed through advanced agentic workflows and extensive human-in-the-loop annotations by 37 annotators from across the Arab world, PEARL comprises over 309K multimodal examples spanning ten culturally significant domains covering all Arab countries. We further provide two robust evaluation benchmarks (PEARL and PEARL-LITE) along with a specialized subset (PEARL-X) explicitly developed to assess nuanced cultural variations. Comprehensive evaluations on state-of-the-art open and proprietary LVLMs demonstrate that reasoning-centric instruction alignment substantially improves models' cultural grounding compared to conventional scaling methods. PEARL establishes a foundational resource for advancing culturally-informed multimodal modeling research. All datasets and benchmarks are publicly available.

Issam Ait Yahia, Ismail Berrada

Anomaly detection in real-world time-series data is a challenging task due to the complex and nonlinear temporal dynamics involved. This paper introduces KoopAGRU, a new deep learning model designed to tackle this problem by combining Fast Fourier Transform (FFT), Deep Dynamic Mode Decomposition (DeepDMD), and Koopman theory. FFT allows KoopAGRU to decompose temporal data into time-variant and time-invariant components providing precise modeling of complex patterns. To better control these two components, KoopAGRU utilizes Gate Recurrent Unit (GRU) encoders to learn Koopman observables, enhancing the detection capability across multiple temporal scales. KoopAGRU is trained in a single process and offers fast inference times. Extensive tests on various benchmark datasets show that KoopAGRU outperforms other leading methods, achieving a new average F1-score of 90.88\% on the well-known anomalies detection task of times series datasets, and proves to be efficient and reliable in detecting anomalies in real-world scenarios.

Abdellah El Mekki, Samar M. Magdy, Houdaifa Atou et al.

Arabic is a highly diglossic language where most daily communication occurs in regional dialects rather than Modern Standard Arabic. Despite this, machine translation (MT) systems often generalize poorly to dialectal input, limiting their utility for millions of speakers. We introduce \textbf{Alexandria}, a large-scale, community-driven, human-translated dataset designed to bridge this gap. Alexandria covers 13 Arab countries and 11 high-impact domains, including health, education, and agriculture. Unlike previous resources, Alexandria provides unprecedented granularity by associating contributions with city-of-origin metadata, capturing authentic local varieties beyond coarse regional labels. The dataset consists of multi-turn conversational scenarios annotated with speaker-addressee gender configurations, enabling the study of gender-conditioned variation in dialectal use. Comprising 107K total samples, Alexandria serves as both a training resource and a rigorous benchmark for evaluating MT and Large Language Models (LLMs). Our automatic and human evaluation of Arabic-aware LLMs benchmarks current capabilities in translating across diverse Arabic dialects and sub-dialects, while exposing significant persistent challenges.

Salmane Chafik, Saad Ezzini, Ismail Berrada

The task of converting natural language questions (NLQs) into executable SQL queries, known as text-to-SQL, has gained significant interest in recent years, as it enables non-technical users to interact with relational databases. Many benchmarks, such as SPIDER and WikiSQL, have contributed to the development of new models and the evaluation of their performance. In addition, other datasets, like SEDE and BIRD, have introduced more challenges and complexities to better map real-world scenarios. However, these datasets primarily focus on high-resource languages such as English and Chinese. In this work, we introduce Dialect2SQL, the first large-scale, cross-domain text-to-SQL dataset in an Arabic dialect. It consists of 9,428 NLQ-SQL pairs across 69 databases in various domains. Along with SQL-related challenges such as long schemas, dirty values, and complex queries, our dataset also incorporates the complexities of the Moroccan dialect, which is known for its diverse source languages, numerous borrowed words, and unique expressions. This demonstrates that our dataset will be a valuable contribution to both the text-to-SQL community and the development of resources for low-resource languages.

Abdellah El Mekki, Abdelkader El Mahdaouy, Kabil Essefar et al.

Dialect and standard language identification are crucial tasks for many Arabic natural language processing applications. In this paper, we present our deep learning-based system, submitted to the second NADI shared task for country-level and province-level identification of Modern Standard Arabic (MSA) and Dialectal Arabic (DA). The system is based on an end-to-end deep Multi-Task Learning (MTL) model to tackle both country-level and province-level MSA/DA identification. The latter MTL model consists of a shared Bidirectional Encoder Representation Transformers (BERT) encoder, two task-specific attention layers, and two classifiers. Our key idea is to leverage both the task-discriminative and the inter-task shared features for country and province MSA/DA identification. The obtained results show that our MTL model outperforms single-task models on most subtasks.

Abdelkader El Mahdaouy, Abdellah El Mekki, Kabil Essefar et al.

The prominence of figurative language devices, such as sarcasm and irony, poses serious challenges for Arabic Sentiment Analysis (SA). While previous research works tackle SA and sarcasm detection separately, this paper introduces an end-to-end deep Multi-Task Learning (MTL) model, allowing knowledge interaction between the two tasks. Our MTL model's architecture consists of a Bidirectional Encoder Representation from Transformers (BERT) model, a multi-task attention interaction module, and two task classifiers. The overall obtained results show that our proposed model outperforms its single-task counterparts on both SA and sarcasm detection sub-tasks.

ElMehdi Boujou, Hamza Chataoui, Abdellah El Mekki et al.

Natural Language Processing (NLP) is today a very active field of research and innovation. Many applications need however big sets of data for supervised learning, suitably labelled for the training purpose. This includes applications for the Arabic language and its national dialects. However, such open access labeled data sets in Arabic and its dialects are lacking in the Data Science ecosystem and this lack can be a burden to innovation and research in this field. In this work, we present an open data set of social data content in several Arabic dialects. This data was collected from the Twitter social network and consists on +50K twits in five (5) national dialects. Furthermore, this data was labeled for several applications, namely dialect detection, topic detection and sentiment analysis. We publish this data as an open access data to encourage innovation and encourage other works in the field of NLP for Arabic dialects and social media. A selection of models were built using this data set and are presented in this paper along with their performances.