Li, Ziqing;
Cukurova, Mutlu;
Bulathwela, Sahan;
(2025)
A Novel Approach to Scalable and Automatic Topic-Controlled Question Generation in Education.
In:
Proceedings of the 15th International Learning Analytics and Knowledge Conference.
(pp. pp. 148-158).
ACM
Preview |
Text
Bulathwela_A Novel Approach to Scalable and Automatic Topic-Controlled Question Generation in Education_VoR.pdf Download (1MB) | Preview |
Abstract
The development of Automatic Question Generation (QG) models has the potential to significantly improve educational practices by reducing the teacher workload associated with creating educational content. This paper introduces a novel approach to educational question generation that controls the topical focus of questions. The proposed Topic-Controlled Question Generation (T-CQG) method enhances the relevance and effectiveness of the generated content for educational purposes. Our approach uses fine-tuning on a pre-trained T5-small model, employing specially created datasets tailored to educational needs. The research further explores the impacts of pre-training strategies, quantisation, and data augmentation on the model’s performance. We specifically address the challenge of generating semantically aligned questions with paragraph-level contexts, thereby improving the topic specificity of the generated questions. In addition, we introduce and explore novel evaluation methods to assess the topical relatedness of the generated questions. Our results, validated through rigorous offline and human-backed evaluations, demonstrate that the proposed models effectively generate high-quality, topic-focused questions. These models have the potential to reduce teacher workload and support personalised tutoring systems by serving as bespoke question generators. With its relatively small number of parameters, the proposals not only advance the capabilities of question generation models for handling specific educational topics but also offer a scalable solution that reduces infrastructure costs. This scalability makes them feasible for widespread use in education without reliance on proprietary large language models like ChatGPT.
| Type: | Proceedings paper |
|---|---|
| Title: | A Novel Approach to Scalable and Automatic Topic-Controlled Question Generation in Education |
| Event: | LAK '25: The 15th International Learning Analytics and Knowledge Conference |
| ISBN-13: | 979-8-4007-0701-8 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1145/3706468.3706487 |
| Publisher version: | https://doi.org/10.1145/3706468.3706487 |
| Language: | English |
| Additional information: | © 2025 Copyright held by the owner/author(s). This work is licensed under a Creative Commons Attribution 4.0 International License (https://creativecommons.org/licenses/by/4.0/). |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > School of Education UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > School of Education > UCL Institute of Education UCL > Provost and Vice Provost Offices > School of Education > UCL Institute of Education > IOE - Culture, Communication and Media UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10205997 |
Loading...
Loading...Loading...| 1. |  United Kingdom | 3 |
| 2. |  Europe | 1 |
Archive Staff Only
 |
View Item |
