Journal of Computing in Higher Education

, Volume 3, Issue 1, pp 36–61 | Cite as

Automated explanation for educational applications

  • Daniel D. Suthers


THE ACTIVITY OF EXPLAINING has been studied and modeled by Artificial Intelligence researchers for almost two decades. While no stand-alone educational applications have resulted, a number of techniques have been developed that, when combined in the right way, can support automated explanation facilities capable of playing a useful role as one educational resource amongst others. In this paper, I will briefly survey the available techniques and evaluate their utility in generating explanations. I then show how these techniques are combined in the design of a computer program that provides explanations in response to questions in physical science domains and discuss the contribution such a facility could make to the computer-based educational environments of the future.


Hybrid Architecture Plan Critic Hybrid Representation Natural Language Generation Educational Application 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Appelt, D. (1985). Planning English referring expressions.Artificial Intelligence, 26(1), 1–33.CrossRefGoogle Scholar
  2. Beiser, A. (1973).Physics. Reading, MA: Addison-Wesley Publising Company, Inc.Google Scholar
  3. Cawsey, A. (1991). Generating interactive explanations.Proceedings of the Ninth National Conference on Artificial Intelligence (pp. 86–91). Anaheim, California.Google Scholar
  4. Cohen, R., & Jones, M. (1987). Incorporating user models into an expert system for educational diagnosis. In W. Wahlster & A. Kobsa (Eds.),User Models in Dialog Systems. London: Springer-Verlag.Google Scholar
  5. Cornell, M., Suthers, D., & Woolf, B. (1991, July). Using “live information≓ in a multimedia framework.Workshop on Intelligent Multimedia Interfaces, Ninth National Conference on Artificial Intelligence (pp. 93–98). Anaheim, California.Google Scholar
  6. Davis, R., Buchanan, B., & Shortliffe, E. (1977). Production rules as a representation for a knowledge-based consultation program.Artificial Intelligence, 8(1), 15–45.CrossRefGoogle Scholar
  7. Horney, M. (1991, Spring). Uses of hypertext.Journal of Computing in Higher Education, 2(2), 44–65.CrossRefGoogle Scholar
  8. Hovy, E. (1990). Pragmatics and natural language generation.Artificial Intelligence, 43(2), 153–197.CrossRefGoogle Scholar
  9. Lester, J., & Porter, P. (1991, July). An architecture for planning multi-paragraph pedagogical explanations.Workshop on Comparative Analysis of Explanation Planning Architectures, Ninth National Conference on Artificial Intelligence (pp. 27–41). Anaheim, California.Google Scholar
  10. Macaulay, D. (1988).The way things work. Boston: Houghton Mifflin Company.Google Scholar
  11. Maybury, M. (1990).Planning multisentential english text using communicative acts. Unpublished doctoral dissertation, Cambridge University.Google Scholar
  12. McCoy, K. (1989). Generating context-sensitive responses to object-related misconceptions.Artificial Intelligence, 41(2), 157–195.CrossRefGoogle Scholar
  13. McKeown, K. (1985). Discourse strategies for generating natural language text.Artificial Intelligence, 27(1), 1–41.CrossRefGoogle Scholar
  14. McKeown, K., Wish, M., & Matthews, K. (1985, August). Tailoring explanations for the user.Proceedings of the Ninth International Joint Conference on Artificial Intelligence (pp. 794–798). Los Angeles, California.Google Scholar
  15. Mooney, D., Carberry, S., & McCoy, K. (in press). Capturing high-level structure of naturally-occurring, extended explanations using bottom-up strategies.Computational Intelligence,7(4).Google Scholar
  16. Moore, J., & Swartout, W. (1989). A reactive approach to explanation.Proceedings of the Eleventh International Joint Conference on Artificial Intelligence. Detroit, Michigan.Google Scholar
  17. Murray, T., & Woolf, B. (1991). A knowledge acquisition framework for intelligent learning environments.Special Interest Group on Artificial Intelligence Bulletin, 2(2), 1–13.Google Scholar
  18. Paris, C., & McKeown, K. (1986). Discourse strategies for describing complex physical objects.Proceedings of the NATO Advanced Research Workshop on Natural Language Generation (pp. 97–115). Nijmegen, The Netherlands.Google Scholar
  19. Stevens, A., & Collins, A. (1980). Multiple conceptual models of a complex system. In R. Snow, P. Federico, & W. Montague (Eds.),Aptitude, Learning, and Instruction, 2, (pp. 177–197). Hillsdale, NJ: Erlbaum.Google Scholar
  20. Suthers, D. (1989).Perspectives in explanation (COINS Technical Report 89-24). Amherst: University of Massachusetts, Computer and Information Science.Google Scholar
  21. Suthers, D. (in press). A task-appropriate hybrid architecture for explanation.Computational Intelligence,7(4).Google Scholar
  22. White, B., & Frederiksen, J. (1990). Causal model progressions as a foundation for intelligent learning environments.Artificial Intelligence, 42(1), 99–157.CrossRefGoogle Scholar
  23. Zukerman, I. (1990). Generating peripheral rhetorical devices by consulting a user model.Fifth International Workshop onNatural Language Generation (pp. 156–163). Dawson, Pennsylvania.Google Scholar

Copyright information

© Springer 1991

Authors and Affiliations

  • Daniel D. Suthers
    • 1
  1. 1.University of MassachusettsUSA

Personalised recommendations