A real-time multiple-choice question generation for language testing: a preliminary study

  • Authors:
  • Ayako Hoshino;Hiroshi Nakagawa

  • Affiliations:
  • University of Tokyo, Bunkyo, Tokyo, Japan;University of Tokyo, Bunkyo, Tokyo, Japan

  • Venue:
  • EdAppsNLP 05 Proceedings of the second workshop on Building Educational Applications Using NLP
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

An automatic generation of multiple-choice questions is one of the promising examples of educational applications of NLP techniques. A machine learning approach seems to be useful for this purpose because some of the processes can be done by classification. Using basic machine learning algorithms as Naive Bayes and K-Nearest Neighbors, we have developed a real-time system which generates questions on English grammar and vocabulary from on-line news articles. This paper describes the current version of our system and discusses some of the issues on constructing this kind of system.