Pre-training with Scientific Text Improves Educational Question Generation (Student Abstract)

With the boom of digital educational materials and scalable e-learning systems, the potential for realising AI-assisted personalised learning has skyrocketed. In this landscape, the automatic generation of educational questions will play a key role, enabling scalable self-assessment when a global population is manoeuvring their personalised learning journeys. We develop EduQG, a novel educational question generation model built by adapting a large language model. Our initial experiments demonstrate that EduQG can produce superior educational questions by pre-training on scientific text.

Authors

• Hamze Muse University College London
• Sahan Bulathwela University College London
• Emine Yilmaz University College London

Keywords

• Educational Question Generation
• Educational Recommenders
• Finetuning
• Intelligent Tutoring System
• Pretraining