Exploring Artificial Jabbering For Automatic Text Comprehension Question Generation
Key: SFR20-2
Author: Tim Steuer, Anna Filighera, Christoph Rensing
Date: September 2020
Kind: In proceedings
Publisher: Springer International Publishing
Book title: European Conference on Technology Enhanced Learning
Abstract: Many educational texts lack comprehension questions andauthoring them consumes time and money. Thus, in this article, we askourselves to what extent artificial jabbering text generation systems canbe used to generate textbook comprehension questions. Novel machinelearning-based text generation systems jabber on a wide variety of top-ics with deceptively good performance. To expose the generated texts assuch, one often has to understand the actual topic the systems jabbersabout. Hence, confronting learners with generated texts may cause themto question their level of knowledge. We built a novel prototype thatgenerates comprehension questions given arbitrary textbook passages.We discuss the strengths and weaknesses of the prototype quantitativelyand qualitatively. While our prototype is not perfect, we provide evidencethat such systems have great potential as question generators and iden-tify the most promising starting points may leading to (semi) automatedgenerators that support textbook authors and self-studying.
View Full paper (PDF) | Download Full paper (PDF)
Official URL

The documents distributed by this server have been provided by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a non-commercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, not withstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.