Communication Dans Un Congrès Année : 2025

Assessing learning materials: hybrid vs Large Language Model-based generation of grammar exercises

Résumé

In this paper, we compare two methods for automatic generation of grammar exercises from authentic texts: (i) a hybrid method where texts are first fed to a neural syntactic parser in order to get morpho-syntactic annotations, from which grammar concepts (e.g. direct objects of verbs) are automatically extracted using handcrafted rules (and then turned into grammar questions), and (ii) a Large Language Model (LLM) -based method where grammar concepts are extracted directly from texts using few shot learning. Concept extraction is evaluated against manually annotated data for French coming from the SEQUOIA treebank, using grammar concepts from French elementary and middle school curricula. Preliminary results show that hybrid approaches offer a viable alternative to pre-trained LLMs in the context of grammar exercise generation.

Fichier principal
Vignette du fichier
publication_gramex (1).pdf (763.64 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05138160 , version 1 (01-07-2025)

Licence

Identifiants

  • HAL Id : hal-05138160 , version 1

Citer

Lucas Poirot, Yannick Parmentier. Assessing learning materials: hybrid vs Large Language Model-based generation of grammar exercises. EvalLAC’25: 2nd Workshop on Automatic Evaluation of Learning and Assessment Content, Jul 2025, Palermo, Italy. ⟨hal-05138160⟩
356 Consultations
230 Téléchargements

Partager

  • More