Episode 24 of the CS@Manchester podcast features a conversation between PhD student Ghader Kurdi from Saudi Arabia and her supervisor Dr Bijan Parsia.
We discuss Ghader's initial journey to start her PhD in the UK and then onto her research in writing Multiple Choice questions* examinations and how it has expanded into other research domains and disciplines.
Stay in touch with the School of Computer Science by following us on Twitter.
*Full abstract from Ghader's paper:
Abstract Designing good multiple choice questions (MCQs) for education and assessment is time consuming and error-prone. An abundance of structured and semi structured data has led to the development of automatic MCQ generation methods. Recently, ontologies have emerged as powerful tools to enable the automatic
generation of MCQs.
However, current ontology-based approaches focus on, mostly simple, knowledge recall questions. In addition, questions that have so far been generated are, compared to manually created ones,
simple and cover only a small subset of the required question complexity space in the education and assessment domain.
We present a novel ontology-based approach that exploits classes and existential restrictions to generate questions with complex stems and are suitable for scenarios beyond mere knowledge recall.
We implement our approach as an application for a medical education scenario on top of a large knowledge base in the medical domain. We generate more than 3 million questions for four physician specialities and evaluate our approach in a user study with 15 medical experts.
We find that, using a stratifed random sample of 435 questions out of which 316 were rated by two experts, 129 (30%) are considered exam-ready by both experts and a further 216 (50%) by at least one expert.
