Assessing French Readability for Adults with Low Literacy: A Global and Local Perspective
(2025) 2025 Conference on Empirical Methods in Natural Language Processing — Location: Suzhou, China (4.November.2025)
Files
2025emnlp-main1036.pdf
Open Access - Adobe PDF
- 489.25 KB
Details
- Authors
Souza Wilkens, Rodrigo 
- Abstract
- 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.
- Affiliations
Citations
Aissa, W., Bañeras-Roux, T., Vanzeveren, E., Gao, L., Souza Wilkens, R., & François, T. (2025). Assessing French Readability for Adults with Low Literacy: A Global and Local Perspective. In Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng (ed.), Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (p. p. 20517–20539). Association for Computational Linguistics. https://doi.org/10.18653/v1/2025.emnlp-main.1036