Grammar Control in Dialogue Response Generation for Language Learning Chatbots
This addresses the need for language learners to practice specific grammar forms, though it is incremental as it builds on existing chatbot and language acquisition research.
The paper tackles the problem of controlling grammar in dialogue response generation for language learning chatbots by grounding models in a pedagogical grammar repository, and it shows that strategically decoding Llama3 outperforms GPT-3.5 with minor quality losses.
Chatbots based on large language models offer cheap conversation practice opportunities for language learners. However, they are hard to control for linguistic forms that correspond to learners' current needs, such as grammar. We control grammar in chatbot conversation practice by grounding a dialogue response generation model in a pedagogical repository of grammar skills. We also explore how this control helps learners to produce specific grammar. We comprehensively evaluate prompting, fine-tuning, and decoding strategies for grammar-controlled dialogue response generation. Strategically decoding Llama3 outperforms GPT-3.5 when tolerating minor response quality losses. Our simulation predicts grammar-controlled responses to support grammar acquisition adapted to learner proficiency. Existing language learning chatbots and research on second language acquisition benefit from these affordances. Code available on GitHub.