QG-Net: A Data-Driven question generation model for educational content

Zichao Wang, Andrew S. Lan, Weili Nie, Andrew E. Waters, Phillip J. Grimaldi, Richard G. Baraniuk

Research output: Chapter in Book/Report/Conference proceedingConference contribution

69 Scopus citations

Abstract

The ever growing amount of educational content renders it increasingly difficult to manually generate sufficient practice or quiz questions to accompany it. This paper introduces QG-Net, a recurrent neural network-based model specifically designed for automatically generating quiz questions from educational content such as textbooks. QG-Net, when trained on a publicly available, general-purpose question/answer dataset and without further fine-tuning, is capable of generating high quality questions from textbooks, where the content is significantly different from the training data. Indeed, QG-Net outperforms state-of-the-art neural network-based and rules-based systems for question generation, both when evaluated using standard benchmark datasets and when using human evaluators. QGNet also scales favorably to applications with large amounts of educational content, since its performance improves with the amount of training data.

Original languageEnglish (US)
Title of host publicationProceedings of the 5th Annual ACM Conference on Learning at Scale, L at S 2018
PublisherAssociation for Computing Machinery, Inc
ISBN (Electronic)9781450358866
DOIs
StatePublished - Jun 26 2018
Event5th Annual ACM Conference on Learning at Scale, L at S 2018 - London, United Kingdom
Duration: Jun 26 2018Jun 28 2018

Publication series

NameProceedings of the 5th Annual ACM Conference on Learning at Scale, L at S 2018

Other

Other5th Annual ACM Conference on Learning at Scale, L at S 2018
Country/TerritoryUnited Kingdom
CityLondon
Period6/26/186/28/18

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Education
  • Software
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'QG-Net: A Data-Driven question generation model for educational content'. Together they form a unique fingerprint.

Cite this