Controlled Language Generation for Language Learning Items
This addresses the need for automated, tailored content creation in language learning applications, though it is incremental in applying existing NLG methods to this domain.
The paper tackled generating English language learning items with controlled proficiency levels and grammar, achieving high grammaticality scores (3.4+ out of 4) and improvements in length (24%) and complexity (9%) over baselines for advanced models.
This work aims to employ natural language generation (NLG) to rapidly generate items for English language learning applications: this requires both language models capable of generating fluent, high-quality English, and to control the output of the generation to match the requirements of the relevant items. We experiment with deep pretrained models for this task, developing novel methods for controlling items for factors relevant in language learning: diverse sentences for different proficiency levels and argument structure to test grammar. Human evaluation demonstrates high grammatically scores for all models (3.4 and above out of 4), and higher length (24%) and complexity (9%) over the baseline for the advanced proficiency model. Our results show that we can achieve strong performance while adding additional control to ensure diverse, tailored content for individual users.