A Novel Approach to Scalable and Automatic Topic-Controlled Question Generation in Education
- URL: http://arxiv.org/abs/2501.05220v1
- Date: Thu, 09 Jan 2025 13:13:24 GMT
- Title: A Novel Approach to Scalable and Automatic Topic-Controlled Question Generation in Education
- Authors: Ziqing Li, Mutlu Cukurova, Sahan Bulathwela,
- Abstract summary: 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 results, validated through rigorous offline and human-backed evaluations, demonstrate that the proposed models effectively generate high-quality, topic-focused questions.
- Score: 6.9238760403459425
- License:
- 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.
Related papers
- Leveraging In-Context Learning and Retrieval-Augmented Generation for Automatic Question Generation in Educational Domains [0.4857223913212445]
This work focuses on advanced techniques for automated question generation in educational contexts.
We implement GPT-4 for ICL using few-shot examples and BART with a retrieval module for RAG.
The Hybrid Model combines RAG and ICL to address these issues and improve question quality.
arXiv Detail & Related papers (2025-01-29T03:25:19Z) - Leveraging Large Language Models to Generate Course-specific Semantically Annotated Learning Objects [2.1845291030915974]
Recent progress in generative natural language models has opened up new potential in the generation of educational content.
This paper explores the potential of large language models for generating computer science questions that are sufficiently annotated for automatic learner model updates.
arXiv Detail & Related papers (2024-12-05T14:24:07Z) - SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models [54.78329741186446]
We propose a novel paradigm that uses a code-based critic model to guide steps including question-code data construction, quality control, and complementary evaluation.
Experiments across both in-domain and out-of-domain benchmarks in English and Chinese demonstrate the effectiveness of the proposed paradigm.
arXiv Detail & Related papers (2024-08-28T06:33:03Z) - Research on the Application of Large Language Models in Automatic Question Generation: A Case Study of ChatGLM in the Context of High School Information Technology Curriculum [3.0753648264454547]
The model is guided to generate diverse questions, which are then comprehensively evaluated by domain experts.
The results indicate that ChatGLM outperforms human-generated questions in terms of clarity and teachers' willingness to use.
arXiv Detail & Related papers (2024-08-21T11:38:32Z) - Automating question generation from educational text [1.9325905076281444]
The use of question-based activities (QBAs) is wide-spread in education, forming an integral part of the learning and assessment process.
We design and evaluate an automated question generation tool for formative and summative assessment in schools.
arXiv Detail & Related papers (2023-09-26T15:18:44Z) - Practical and Ethical Challenges of Large Language Models in Education:
A Systematic Scoping Review [5.329514340780243]
Large language models (LLMs) have the potential to automate the laborious process of generating and analysing textual content.
There are concerns regarding the practicality and ethicality of these innovations.
We conducted a systematic scoping review of 118 peer-reviewed papers published since 2017 to pinpoint the current state of research.
arXiv Detail & Related papers (2023-03-17T18:14:46Z) - What should I Ask: A Knowledge-driven Approach for Follow-up Questions
Generation in Conversational Surveys [63.51903260461746]
We propose a novel task for knowledge-driven follow-up question generation in conversational surveys.
We constructed a new human-annotated dataset of human-written follow-up questions with dialogue history and labeled knowledge.
We then propose a two-staged knowledge-driven model for the task, which generates informative and coherent follow-up questions.
arXiv Detail & Related papers (2022-05-23T00:57:33Z) - Quiz Design Task: Helping Teachers Create Quizzes with Automated
Question Generation [87.34509878569916]
This paper focuses on the use case of helping teachers automate the generation of reading comprehension quizzes.
In our study, teachers building a quiz receive question suggestions, which they can either accept or refuse with a reason.
arXiv Detail & Related papers (2022-05-03T18:59:03Z) - Educational Question Generation of Children Storybooks via Question Type Distribution Learning and Event-Centric Summarization [67.1483219601714]
We propose a novel question generation method that first learns the question type distribution of an input story paragraph.
We finetune a pre-trained transformer-based sequence-to-sequence model using silver samples composed by educational question-answer pairs.
Our work indicates the necessity of decomposing question type distribution learning and event-centric summary generation for educational question generation.
arXiv Detail & Related papers (2022-03-27T02:21:19Z) - Inquisitive Question Generation for High Level Text Comprehension [60.21497846332531]
We introduce INQUISITIVE, a dataset of 19K questions that are elicited while a person is reading through a document.
We show that readers engage in a series of pragmatic strategies to seek information.
We evaluate question generation models based on GPT-2 and show that our model is able to generate reasonable questions.
arXiv Detail & Related papers (2020-10-04T19:03:39Z) - Enhancing Dialogue Generation via Multi-Level Contrastive Learning [57.005432249952406]
We propose a multi-level contrastive learning paradigm to model the fine-grained quality of the responses with respect to the query.
A Rank-aware (RC) network is designed to construct the multi-level contrastive optimization objectives.
We build a Knowledge Inference (KI) component to capture the keyword knowledge from the reference during training and exploit such information to encourage the generation of informative words.
arXiv Detail & Related papers (2020-09-19T02:41:04Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.