Fully Automated Generation of Question-Answer Pairs for Scripted Virtual Instruction

  • Pascal Kuyten
  • Timothy Bickmore
  • Svetlana Stoyanchev
  • Paul Piwek
  • Helmut Prendinger
  • Mitsuru Ishizuka
Conference paper

DOI: 10.1007/978-3-642-33197-8_1

Part of the Lecture Notes in Computer Science book series (LNCS, volume 7502)
Cite this paper as:
Kuyten P., Bickmore T., Stoyanchev S., Piwek P., Prendinger H., Ishizuka M. (2012) Fully Automated Generation of Question-Answer Pairs for Scripted Virtual Instruction. In: Nakano Y., Neff M., Paiva A., Walker M. (eds) Intelligent Virtual Agents. IVA 2012. Lecture Notes in Computer Science, vol 7502. Springer, Berlin, Heidelberg

Abstract

We introduce a novel approach for automatically generating a virtual instructor from textual input only. Our fully implemented system first analyzes the rhetorical structure of the input text and then creates various question-answer pairs using patterns. These patterns have been derived from correlations found between rhetorical structure of monologue texts and question-answer pairs in the corresponding dialogues. A selection of the candidate pairs is verbalized into a diverse collection of question-answer pairs. Finally the system compiles the collection of question-answer pairs into scripts for a virtual instructor. Our end-to-end system presents questions in pre-fixed order and the agent answers them. Our system was evaluated with a group of twenty-four subjects. The evaluation was conducted using three informed consent documents of clinical trials from the domain of colon cancer. Each of the documents was explained by a virtual instructor using 1) text, 2) text and agent monologue, and 3) text and agent performing question-answering. Results show that an agent explaining an informed consent document did not provide significantly better comprehension scores, but did score higher on satisfaction, compared to two control conditions.

Keywords

Dialogue Generation Rhetorical Structure Theory Medical Documents 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Pascal Kuyten
    • 1
  • Timothy Bickmore
    • 2
  • Svetlana Stoyanchev
    • 3
  • Paul Piwek
    • 4
  • Helmut Prendinger
    • 5
  • Mitsuru Ishizuka
    • 1
  1. 1.Graduate School of Information Science & TechnologyThe University of TokyoJapan
  2. 2.College of Computer and Information ScienceNortheastern UniversityBostonUSA
  3. 3.Spoken Language Processing Group, Department of Computer ScienceColumbia UniversityNew YorkUSA
  4. 4.NLG Group, Centre for Research in ComputingThe Open UniversityWalton HallUK
  5. 5.National Institute of InformaticsTokyoJapan

Personalised recommendations