Storyfier: Exploring Vocabulary Learning Support with Text Generation Models
This addresses vocabulary learning for students and teachers, but it is incremental as it builds on existing text generation models for educational support.
The paper tackled the problem of vocabulary learning tools lacking coherent contexts for arbitrary target words and insufficient practice in word usage by developing Storyfier, which uses text generation models to create stories, cloze tests, and writing assistance. The result showed that learners favored the generated stories and writing help, but participants performed worse in recalling and using target words compared to a baseline tool without AI features.
Vocabulary learning support tools have widely exploited existing materials, e.g., stories or video clips, as contexts to help users memorize each target word. However, these tools could not provide a coherent context for any target words of learners' interests, and they seldom help practice word usage. In this paper, we work with teachers and students to iteratively develop Storyfier, which leverages text generation models to enable learners to read a generated story that covers any target words, conduct a story cloze test, and use these words to write a new story with adaptive AI assistance. Our within-subjects study (N=28) shows that learners generally favor the generated stories for connecting target words and writing assistance for easing their learning workload. However, in the read-cloze-write learning sessions, participants using Storyfier perform worse in recalling and using target words than learning with a baseline tool without our AI features. We discuss insights into supporting learning tasks with generative models.