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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ledoyen, François, Dias, Gaël, Lechervy, Alexis, Pantin, Jeremie, Maurel, Fabrice, Chahir, Youssef, Gouzonnat, Elisa, Berthelot, Mélanie, Moravac, Stanislas, Altinier, Armony, Khairalla, Amy
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914070080258048
author Ledoyen, François
Dias, Gaël
Lechervy, Alexis
Pantin, Jeremie
Maurel, Fabrice
Chahir, Youssef
Gouzonnat, Elisa
Berthelot, Mélanie
Moravac, Stanislas
Altinier, Armony
Khairalla, Amy
author_facet Ledoyen, François
Dias, Gaël
Lechervy, Alexis
Pantin, Jeremie
Maurel, Fabrice
Chahir, Youssef
Gouzonnat, Elisa
Berthelot, Mélanie
Moravac, Stanislas
Altinier, Armony
Khairalla, Amy
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_00691
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Inclusive Easy-to-Read Generation for Individuals with Cognitive Impairments
Ledoyen, François
Dias, Gaël
Lechervy, Alexis
Pantin, Jeremie
Maurel, Fabrice
Chahir, Youssef
Gouzonnat, Elisa
Berthelot, Mélanie
Moravac, Stanislas
Altinier, Armony
Khairalla, Amy
Computation and Language
Artificial Intelligence
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.
title Inclusive Easy-to-Read Generation for Individuals with Cognitive Impairments
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2510.00691