SRS-Stories: Vocabulary-constrained multilingual story generation for language learning
Preprint
Abstract
In this paper, we use large language models to generate personalized stories for language learners, using only the vocabulary they know. The generated texts are specifically written to teach the user new vocabulary by simply reading stories where it appears in context, while at the same time seamlessly reviewing recently learned vocabulary. The generated stories are enjoyable to read and the vocabulary reviewing/learning is optimized by a Spaced Repetition System. The experiments are conducted in three languages: English, Chinese and Polish, evaluating three story generation methods and three strategies for enforcing lexical constraints. The results show that the generated stories are more grammatical, coherent, and provide better examples of word usage than texts generated by the standard constrained beam search approachKeywords
All Related Versions
- Version 1, 2025-12-20, ArXiv
- Published version: , 630.
This publication has 10 references indexed in Scilit:
- Themis: A Reference-free NLG Evaluation Language Model with Flexibility and Interpretability2024
- GEMBA-MQM: Detecting Translation Quality Error Spans with GPT-42023
- Transformers: State-of-the-Art Natural Language Processing2020
- Neural Network Acceptability JudgmentsTransactions of the Association for Computational Linguistics, 2019
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding2019
- Improved Lexically Constrained Decoding for Translation and Monolingual Rewriting2019
- Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation2018
- Learning to Read Words on Flashcards: Effects of Sentence Contexts and Word Class in Native and Nonnative English-Speaking KindergartnersEarly Childhood Research Quarterly, 2017
- Unbounded Human Learning2016
- Optimization of repetition spacing in the practice of learningActa Neurobiologiae Experimentalis, 1994