A Generative Approach to Enrich Arabic Story Text with Visual Aids

Abstract

Enriching the script of a story with visual aids is an effective approach for promoting language learning and literacy development for young children and learners. In this paper, we propose a new system, that can generate short Arabic stories with generated images that accurately represent the story, scene and context of the given input. We use a text generation technique with a text-to-image synthesis network and minimize the human intervention. We build a corpus of Arabic stories with vocabulary and visualizations. The obtained results with various generative models to create text-image contents show the effectiveness of the proposed approach. The system can be used in education and assist the instructors to build stories on different domains. It can be used in distance learning to deliver online tutorials during COVID-19.