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.