Inclusive Easy-to-Read Generation for Individuals with Cognitive Impairments

2025-10-01

AI Summary

To address the difficulty cognitively impaired individuals face in accessing healthcare, educational, and public information, this paper introduces the first French easy-to-read text generation method compliant with the European Easy-to-Read (ETR) standard. Methodologically, we (1) construct ETR-fr, the first fully ETR-compliant French easy-to-read dataset; (2) propose a lightweight, efficient, and cross-domain adaptable generation framework leveraging parameter-efficient fine-tuning of pretrained and large language models; and (3) establish a rigorous human evaluation protocol aligned with 36 ETR guidelines, complemented by automated metrics. Experimental results demonstrate that our lightweight model achieves performance on par with larger models while exhibiting superior generalization across diverse domains. This work significantly enhances the practicality, scalability, and equitable accessibility of easy-to-read content generation.

Technology Category

• Natural Language Processing: Generation
• Humans and AI: AI for Accessibility
• Application Domains: Humanities & Computational Social Science

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Ensuring accessibility for individuals with cognitive impairments is essential for autonomy, self-determination, and full citizenship. However, manual Easy-to-Read (ETR) text adaptations are slow, costly, and difficult to scale, limiting access to crucial information in healthcare, education, and civic life. AI-driven ETR generation offers a scalable solution but faces key challenges, including dataset scarcity, domain adaptation, and balancing lightweight learning of Large Language Models (LLMs). In this paper, we introduce ETR-fr, the first dataset for ETR text generation fully compliant with European ETR guidelines. We implement parameter-efficient fine-tuning on PLMs and LLMs to establish generative baselines. To ensure high-quality and accessible outputs, we introduce an evaluation framework based on automatic metrics supplemented by human assessments. The latter is conducted using a 36-question evaluation form that is aligned with the guidelines. Overall results show that PLMs perform comparably to LLMs and adapt effectively to out-of-domain texts.

Problem

• Generating accessible texts for cognitive impairments
• Overcoming manual adaptation limitations with AI solutions
• Addressing dataset scarcity and domain adaptation challenges

Innovation

• Created first European guideline-compliant ETR dataset
• Used parameter-efficient fine-tuning on language models
• Introduced automatic and human evaluation framework