Abstract
Multiple choice questions (MCQs) are considered highly useful (being easy to take or mark) but quite difficult to create and large numbers are needed to form valid exams and associated practice materials. The idea of re-using an existing ontology to generate MCQs almost suggests itself and has been explored in various projects. In this project, we are applying suitable educational theory regarding assessments and related methods for their evaluation to ontology-based MCQ generation. In particular, we investigate whether we can measure the similarity of the concepts in an ontology with sufficient reliability so that this measure can be used to control the difficulty of the MCQs generated. In this report, we provide an overview of the background to this research, and describe the main steps taken and insights gained.
Highlights
We investigate whether we can measure the similarity of the concepts in an ontology with sufficient reliability so that this measure can be used to control the difficulty of the Multiple choice questions (MCQs) generated
Description logics (DLs) [4] are well-understood logics that form the logical basis of the web ontology language OWL
We address the first issue in [1] and to address the second issue we conjecture that, given a suitable ontology and a suitable similarity measure on concepts, we can generate MCQs whose difficulty we can control by varying the similarity between the distractors and the key
Summary
Description logics (DLs) [4] are well-understood logics that form the logical basis of the web ontology language OWL. As a consequence of OWL’s standardisation over the past 15 years and the related increase in tool support (e.g., reasoners, editors/IDEs, APIs), loads of people/communities have developed ontologies, i.e., DL knowledge bases that capture some domain of interest, in particular in biology and clinical sciences. Some of these ontologies have been developed by groups of experts over a long time, and so can be expected to provide a shared. An ontology: does it capture enough domain knowledge to base our MCQ generation on it? In particular, is the ontology detailed enough so that we can gauge concepts’ commonalities and differences which, in turn, is a requirement for estimating similarity between concepts?
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
