Robust Multilingual Text-to-Pictogram Mapping for Scalable Reading Rehabilitation

TL;DR

This paper presents an AI-powered multilingual system that automatically maps key text concepts to relevant pictograms, enhancing reading support for children with SEND across diverse languages.

Contribution

It introduces a scalable, multilingual visual scaffolding system that dynamically links text to pictograms, validated across five languages with high semantic accuracy and real-time performance.

Findings

High pictogram coverage across five languages.

Semantic appropriateness rated above 95% for European languages.

System latency suitable for real-time educational use.

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.