Over 5% of the world's population (466 million people) has disabling hearing loss. 4 million are children. They can be hard of hearing or deaf. Deaf people mostly have profound hearing loss. Which implies very little or no hearing. Over the world, deaf people often communicate using a sign language with gestures of both hands and facial expressions. The sign language is a full-fledged natural language with its own grammar and lexicon. Therefore, there is a need for translation models from and to sign languages. In this work, we are interested in the translation of Modern Standard Arabic(MSAr) into sign language. We generated a gloss representation from MSAr that extracts the features mandatory for the generation of animation signs. Our approach locates the most pertinent features that maintain the meaning of the input Arabic sentence.