Communication Dans Un Congrès Année : 2025

Aligning sentence simplification with ESL learner's proficiency for language acquisition

Résumé

Text simplification is crucial for improving accessibility and comprehension for English as a Second Language (ESL) learners. This study goes a step further and aims to facilitate ESL learners' language acquisition by simplification. Specifically, we propose simplifying complex sentences to appropriate levels for learners while also increasing vocabulary coverage of the target level in the simplifications. We achieve this without a parallel corpus by conducting reinforcement learning on a large language model. Our method employs token-level and sentence-level rewards, and iteratively trains the model on its self-generated outputs to guide the model to search for simplification hypotheses that satisfy the target attributes. Experiment results on CEFR-SP and TurkCorpus datasets show that the proposed method can effectively increase the frequency and diversity of vocabulary of the target level by more than 20%

Fichier principal
Vignette du fichier
Controlling_Text_Simplification_with_Language_Learning_Level_Revision_Camera_Ready.pdf (1.95 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04926354 , version 1 (03-02-2025)

Licence

Identifiants

Citer

Guanlin Li, Yuki Arase, Noel Crespi. Aligning sentence simplification with ESL learner's proficiency for language acquisition. Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics(NAACL), Apr 2025, Albuquerque, New Mexico, United States. ⟨10.48550/arXiv.2502.11457⟩. ⟨hal-04926354⟩
150 Consultations
483 Téléchargements

Altmetric

Partager

  • More