Artificial Intelligence

Merlyn research paper on automated question generation accepted at AI-2023

Merlyn Mind
June 21, 2024

A Merlyn research paper on generative AI has been accepted at AI-2023, the 43rd annual International Conference of the British Computer Society's Specialist Group on Artificial Intelligence. The conference is being held in December at Peterhouse College in Cambridge, England.

Abstract: Automating question generation from educational text

The use of question-based activities (QBAs) is widespread in education, traditionally forming an integral part of the learning and assessment process. In this paper, we design and evaluate an automated question-generation tool for formative and summative assessment in schools. We present an expert survey of one hundred and four teachers, demonstrating the need for automated generation of QBAs, as a tool that can significantly reduce the workload of teachers and facilitate personalized learning experiences. Leveraging the recent advancements in generative AI, we then present a modular framework employing transformer-based language models for automatic generation of multiple-choice questions (MCQs) from textual content. The presented solution, with distinct modules for question generation, correct answer prediction, and distractor formulation, enables us to evaluate different language models and generation techniques. Finally, we perform an extensive quantitative and qualitative evaluation, demonstrating trade-offs in the use of different techniques and models.

Read the full paper on arXiv.

All Posts

Merlyn research paper on automated question generation accepted at AI-2023

Artificial Intelligence
June 21, 2024
Merlyn Mind

A Merlyn research paper on generative AI has been accepted at AI-2023, the 43rd annual International Conference of the British Computer Society's Specialist Group on Artificial Intelligence. The conference is being held in December at Peterhouse College in Cambridge, England.

Abstract: Automating question generation from educational text

The use of question-based activities (QBAs) is widespread in education, traditionally forming an integral part of the learning and assessment process. In this paper, we design and evaluate an automated question-generation tool for formative and summative assessment in schools. We present an expert survey of one hundred and four teachers, demonstrating the need for automated generation of QBAs, as a tool that can significantly reduce the workload of teachers and facilitate personalized learning experiences. Leveraging the recent advancements in generative AI, we then present a modular framework employing transformer-based language models for automatic generation of multiple-choice questions (MCQs) from textual content. The presented solution, with distinct modules for question generation, correct answer prediction, and distractor formulation, enables us to evaluate different language models and generation techniques. Finally, we perform an extensive quantitative and qualitative evaluation, demonstrating trade-offs in the use of different techniques and models.

Read the full paper on arXiv.

Book a demo

Schedule a free personalized demo to see our purpose-built solutions in action, and hear how innovative schools are leveraging the power of Merlyn in their classrooms.

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.