Access to information is a major challenge for deaf communities, especially in emergencies where communication is often delivered through spoken or written language that may not be fully accessible to sign language users, and in regions where sign language linguistic resources and technological tools are limited. This paper presents a system for translating Standard Arabic text into Moroccan Sign Language (MSL) using a rule-based architecture enhanced with Large Language Model (LLM)-based lexical disambiguation. The system uses Arabic linguistic analysis, contextual word sense disambiguation, rule-based grammatical transformations, and video-based sign generation to produce sign language output. The main contribution of the system is the introduction of an automated disambiguation mechanism that resolves polysemous Arabic words without requiring manual user intervention. The approach builds on previously developed linguistic resources, including a bilingual Arabic–MSL lexical database with approximately 3000 entries and data collected within the framework of a large-scale MSL corpus project involving deaf participants from the 12 regions of Morocco. Preliminary evaluation shows that contextual disambiguation improves translation performance when ambiguous Arabic words correspond to different MSL signs. The proposed system contributes to the development of accessibility technologies for under-resourced sign languages and supports improved access to information for deaf communities.

This paper presents a set of bilingual Standard Arabic (SA)-Moroccan Sign Language (MSL) tools and resources to improve Moroccan Deaf children’s SA skills. An MSL Generator based on rule-based machine translation (MT) is described that enables users and educators of Deaf children, in particular, to enter Arabic text and generate its corresponding MSL translation in both graphic and video format. The generated graphics can be printed and imported into an Arabic reading passage. We have also developed MSL Clip and Create software that includes a bilingual database of 3,000 MSL signs and SA words, a Publisher for the incorporation of MSL graphic support into SA reading passages, and six Templates that create customized bilingual crossword puzzles, word searches, Bingo cards, matching games, flashcards, and fingerspelling scrambles. A crowdsourcing platform for MSL data collection is also described. A major social benefit of the development of these resources is in relation to equity and the status of deaf people in Moroccan society. More appropriate resources for the bilingual education of Deaf children (in MSL and SA) will lead to improved quality of educational services.

Large Language Models (LLMs) have demonstrated impressive capabilities in various natural language processing tasks across different languages. However, their performance in low-resource languages and dialects, such as Moroccan Arabic (MA), requires further investigation. This study evaluates the performance of ChatGPT-4, different fine-tuned BERT models, FastText as text representation, and traditional machine learning models on MA sentiment analysis. Experiments were done on two open source MA datasets: an X(Twitter) Moroccan Arabic corpus (MAC) and a Moroccan Arabic YouTube corpus (MYC) datasets to assess their capabilities on sentiment text classification. We compare the performance of fully fine-tuned and pre-trained Arabic BERT-based models with ChatGPT-4 in zero-shot settings.