The automatic generation of educational questions will play a key role in
scaling online education, enabling self-assessment at scale when a global
population is manoeuvring their personalised learning journeys.
Question generation is a natural language generation task that can be achieved with a single Transformer-based unidirectional language model, which outperforms QG baselines and produces high-quality questions that are relevant to their context paragraph and easy to answer, utilizing transfer learning without relying on auxiliary data.