Robust Multilingual Text-to-Pictogram Mapping for Scalable Reading Rehabilitation
2026-03-25 • Computation and Language
Computation and LanguageHuman-Computer Interaction
AI summaryⓘ
The authors created an AI tool that helps children with special learning needs understand reading materials better by adding helpful pictures automatically. This tool works in five different languages and matches key words with relevant images to support understanding. Experts checked the images and found that most were accurate and helpful, especially in the European languages tested. The system is fast enough to be used in real-time, showing it can be a practical aid for educators and therapists.
Special Educational Needs and Disabilities (SEND)reading comprehensionAI-powered interfacevisual scaffoldingpictogramsmultilingualspeech therapyneurodiverse learnerslatencysemantic appropriateness
Authors
Soufiane Jhilal, Martina Galletti
Abstract
Reading comprehension presents a significant challenge for children with Special Educational Needs and Disabilities (SEND), often requiring intensive one-on-one reading support. To assist therapists in scaling this support, we developed a multilingual, AI-powered interface that automatically enhances text with visual scaffolding. This system dynamically identifies key concepts and maps them to contextually relevant pictograms, supporting learners across languages. We evaluated the system across five typologically diverse languages (English, French, Italian, Spanish, and Arabic), through multilingual coverage analysis, expert clinical review by speech therapists and special education professionals, and latency assessment. Evaluation results indicate high pictogram coverage and visual scaffolding density across the five languages. Expert audits suggested that automatically selected pictograms were semantically appropriate, with combined correct and acceptable ratings exceeding 95% for the four European languages and approximately 90% for Arabic despite reduced pictogram repository coverage. System latency remained within interactive thresholds suitable for real-time educational use. These findings support the technical viability, semantic safety, and acceptability of automated multimodal scaffolding to improve accessibility for neurodiverse learners.