GELLI generates immersive language practice tailored to learners
GELLI: A Generator for Experiential Language Learning Interactions
Human-Computer Interaction
Summary
Learning a new language is easier when you practice real-life conversations, but making those practice scenarios can take a lot of work. The authors created GELLI, a system that builds unique interactive stories for language learners on the fly, based on what they want to practice. In tests with Japanese learners, GELLI helped people remember words better and feel more confident than watching expert-made videos, while still encouraging safe experimentation and discovery. This system lets learners shape their own experiences instead of only following fixed lessons.
What this means in practice
- •For language learning app developers: Integrate runtime generated conversational scenarios based on learner goals to provide personalized and diverse language practice without pre-created content.$Commercial implications: Enables apps to offer unique, tailored practice worlds dynamically, reducing content creation costs and increasing learner engagement and retention.
- •For virtual reality content creators: Create immersive language learning environments that adapt to user goals with generated narrative scenes and interactive character dialogues at runtime.
Authors
Danilo Symonette, Alan Y. Cheng, Taiga Ikedo, Jose Manuel Rosales Juarez, Roy Pea, Parastoo Abtahi, Jane L. E, James Landay
Abstract
Learning a second language requires extensive practice across situations personal to each learner, yet the most effective existing approaches --- narrative situations designed around specific learning goals and delivered through media --- demand substantial authoring effort, limiting practice to the scope of what was built. We present GELLI, a system that generates narrative practice worlds from a learner's goals: situated scenes with characters to converse with, support alongside the interaction, and reflection, all produced at runtime with no pre authored content. In a within-subjects study with 40 learners of Japanese, GELLI produced greater vocabulary recall and confidence than expert-authored videos targeting the same goals, with no significant difference in speaking performance. Learners turned remembered or imagined situations into experiences they could shape and learn through. Support made experimentation feel safe, while unexpected narrative developments and language suggestions gave them new possibilities to pursue beyond what they initially intended to practice.