AAAI 2023technical13 citations
Pre-training with Scientific Text Improves Educational Question Generation (Student Abstract)
Hamze Muse, Sahan Bulathwela, Emine Yilmaz
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.
BibTeX
@article{Muse_Bulathwela_Yilmaz_2024, title={Pre-training with Scientific Text Improves Educational Question Generation (Student Abstract)}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/27004}, DOI={10.1609/aaai.v37i13.27004}, abstractNote={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.}, number={13}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Muse, Hamze and Bulathwela, Sahan and Yilmaz, Emine}, year={2024}, month={Jul.}, pages={16288-16289} }