Advertisement

Human-to-Machine Interaction in Natural Language: Empirical Results of Field Studies with an English and a German Interface

  • J. Krause

Abstract

Questions of feasibility and desirability of natural langauge interfaces for human-machine interactions gain more and more interest in empirical research. There is growing consensus that field studies provide valuable leads with respect to design decisions.

One of the most important aspects of user friendly interfaces are the restriction rules. The problem is how to restrict the diversity of communicative use of the human native language without losing the advantage of this form of communication with computers.

The paper tries to answer this question on the basis of several empirical studies which investigate the same domain-independent natural langauge query system, using various applications in two different natural languages - - English and German. The studies were performed in cooperation with the IBM Heidelberg Scientific Center (West Germany), the New York University (Advanced Language Project), and the Department of Linguistic Information Science at the University of Regensburg (West Germany). Altogether, these experiments involved about 100 subjects and over 12,000 queries, constituting the bulk of empirical evaluations of natural query language systems reported to date. Results of these experiments are presented and one of the most recent successful software packages Q&A is discussed with respect to the selected restriction rules.

Keywords

Natural Language Query Language Linguistic Information Database Query Restriction Rule 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Bundy, A., ed., 1983, Proceedings of the 8th IJCAI, Karlsruhe.Google Scholar
  2. Carboneil, J. G., 1984, “Is There Natural Language After Databases?”, Proceedings of CQLING 1984, Stanford, pp. 186–187.Google Scholar
  3. Flickinger, D., 1984, “Panel on Natural Language and Databases”, Proceedings of CQLING 1984, Stanford, pp. 188–189.Google Scholar
  4. Gaines, B. R., and Shaw, M. L. G., 1986, “From Time-Sharing to the Sixth Generation: The Development of Human-Computer-Interaction. Part I.,” Intl. J. Man-Machine Studies, 24, pp. 1–27.CrossRefGoogle Scholar
  5. Hirose, K., and Fuchi, K., 1984, The Culture of the Fifth Generation Computer, Tokyo.Google Scholar
  6. Hutchins, E. L., et al., 1986, “Direct Manipulation Interfaces”, User Centered System Design, Norman, D. A., and Draper, S. W., eds., Hillsdale-London, pp. 87–124.Google Scholar
  7. Jarke, M., and Krause, J., 1985, “New Empirical Results of User Studies with a Domain-Independent Natural Language Query System”, Artificial Intelligence Methodology Systems Applications, Bibel, W., and Pettkoff, B., eds., North-Holland, pp. 153–159.Google Scholar
  8. Jarke, M., Krause, J., and Vassiliou, Y., 1986, “Studies in the Evaluation of a Domain-Independent Natural Language Query System”, Cooperative Interactive Information Systems, Bole, L., and Jarke, M., eds., Berlin et al., pp. 101–130.CrossRefGoogle Scholar
  9. Jarke, M., et al., 1985, “A Field Evaluation of Natural Language for Data Retrieval”, IEEE Transactions on Software Engineering, SE-11, (1), pp. 97–114.CrossRefGoogle Scholar
  10. Krause, J., 1982, “Mensch-Maschine-Interaktion in natürlicher Sprache”, Evaluierungsstudien zu praxisorientierten Frage-Antwort-Systemen und ihre Methodik, Tübingen.Google Scholar
  11. Krause, J., 1984, “Praxisorientierte natürlichsprachliche Frage-Antwort- Systems: Zur Entwicklung vor allem in der Bundesrepublik Deutschland”, Nachrichten für Dokumentation, 34, (4/5), pp. 188–194.Google Scholar
  12. Krause, J., and Lehmann, H., 1980, “User Specialty Languages. A Natural Language Based Information System and Its Evaluation”, Dialogsvsteme und Textverarbeitung, Krallmann, D., ed., Essen, pp. 127–146.Google Scholar
  13. Lehmann, H., 1978, “Interpretation of Natural Language in an Information System”, IBM-Journal of Research and Development, 5, pp. 560–572.CrossRefGoogle Scholar
  14. Lehmann, H., and Blaser, A., 1979, Query Languages in Database Systems, IBM Heidelberg Scientific Center Technical Report 79.07.004.Google Scholar
  15. Lehmann, H., Ott, N., and Zoeppritz, M., 1985, “A Multilingual Interface to Databases”, IEEE Database Engineering Bulletin 8.3, September 1985.Google Scholar
  16. McKeown, K. R., 1984, “Natural Language for Expert Systems: Comparison with Database Systems”, Proceedings of CQLING 1984, Stanford, pp. 190–193.Google Scholar
  17. Ott, N., and Zoeppritz, M., 1979, “USL - An Experimental Information System Based on Natural Language”, Natural Communication with Computers, Bole, L., ed., München et al., pp. 3–32.Google Scholar
  18. Shneidermann, B., 1983, “Direct Manipulation: A Step Beyond Programming Languages”, IEEE, 8, pp. 57–69.Google Scholar
  19. Sparck-Jones, K., 1984, “Natural Language and Databases, Again”, Proceedings of CQLING 1984, Stanford, pp. 182–183.Google Scholar
  20. Vassiliou, Y., et al., 1983, “Natural Language for Database Queries: A Laboratory Study”, MIS Quarterly, 7, (4), pp. 47–61.CrossRefGoogle Scholar
  21. Whiteside, J., et al., 1985, “User Performance with Command, Menu, and Iconic Interfaces”, Human Factors in Computer Systems-II. Proceedings of the CHI’85 Conference, Bormann, L., and Curtis, B., eds., Amsterdam, et al., pp. 185–192.Google Scholar
  22. Zoeppritz, M., 1983, “Human Factors of a ‘Natural Language End User System’“, End User Systems and Their Human Factors, Blaser, A., Zoeppritz, M., eds., Berlin et al., pp. 62–93.CrossRefGoogle Scholar
  23. Zoeppritz, M., 1984, Syntax for German in the User Specialty Languages System, Tübingen.Google Scholar
  24. Zoeppritz, M., 1985, “Computer Talk?”, IBM Heidelberg Scientific Center Technical Note 85.05.Google Scholar

Copyright information

© Plenum Press, New York 1987

Authors and Affiliations

  • J. Krause
    • 1
    • 2
  1. 1.IBM Scientific CenterHeidelbergWest Germany
  2. 2.Linguistic Information ScienceUniversity of RegensburgWest Germany

Personalised recommendations