| Title: |
Assessing French Readability for Adults with Low Literacy: A Global and Local Perspective |
| Authors: |
Aissa, Wafa; Bañeras-Roux, Thibault; Vanzeveren, Elodie; Gao, Lingyun; Souza Wilkens, Rodrigo; François, Thomas; 2025 Conference on Empirical Methods in Natural Language Processing |
| Contributors: |
UCL - SSH/ILC/PLIN - Pôle de recherche en linguistique; UCL - SSH/TALN - Centre de traitement automatique du langage |
| Publisher Information: |
Association for Computational Linguistics |
| Publication Year: |
2025 |
| Collection: |
DIAL@USL-B (Université Saint-Louis, Bruxelles) |
| Description: |
This study presents a novel approach to assessing French text readability for adults with low literacy skills, addressing both global (full-text) and local (segment-level) difficulty. We introduce a dataset of 461 texts annotated using a difficulty scale developed specifically for this population. Using this corpus, we conducted a systematic comparison of key readability modeling approaches, including machine learning techniques based on linguistic variables, fine-tuning of CamemBERT, a hybrid approach combining CamemBERT with linguistic variables, and the use of generative language models (LLMs) to carry out readability assessment at both global and local levels. |
| Document Type: |
conference object |
| Language: |
English |
| Relation: |
info:eu-repo/grantAgreement/European Commission/HORIZON- CL2-2022-TRANSFORMATIONS-01-07/1010094837; info:eu-repo/grantAgreement/FNRS/PDR/40013622; boreal:310339; https://hdl.handle.net/2078.1/310339 |
| DOI: |
10.18653/v1/2025.emnlp-main.1036 |
| Availability: |
https://hdl.handle.net/2078.1/310339; https://doi.org/10.18653/v1/2025.emnlp-main.1036 |
| Rights: |
info:eu-repo/semantics/openAccess |
| Accession Number: |
edsbas.E9B7C535 |
| Database: |
BASE |