Question Generation Using WordNet

Abstract

Discourse and argumentation are effective techniques for education not only in social domains but also in science domains. However, it is difficult for some teachers to stimulate an active discussion between students because several students might not be able to develop their arguments. In this paper, we propose to use WordNet as a semantic source in order to generate questions that are intended to stimulate students brainstorming and to help them develop arguments in an argumentation process. In a study, we demonstrate that the system-generated questions sound naturally as human-generated questions as measured by computer scientists.