A meta-rule approach to flexible plan recognition in dialogue

  • Rhonda Eller
  • Sandra Carberry
Article

Abstract

Although a number of researchers have demonstrated that reasoning on a model of the user's plans and goals is helpful in language understanding and response generation, current models of plan inference cannot handle naturally occurring dialogue. This paper argues that model building from less than ideal dialogues has a great deal in common with processing ill-formed input. It defines well-formedness constraints for information-seeking dialogues and contends that strategies for interpreting ill-formed input can be applied to the problem of modeling the user's plan during an ill-formed dialogue. It presents a meta-rule approach for hypothesizing the cause of dialogue ill-formedness, and describes meta-rules for relaxing the plan inference process and enabling the consideration of alternative hypotheses. The advantages of this approach are that it provides a unified framework for handling both well-formed and ill-formed dialogue, avoids unnatural interpretations when the dialogue is proceeding smoothly, and facilitates a nonmonotonic plan recognition system.

Key words

Plan recognition Dialogue Ill-formedness 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Allen, James F. and C. Raymond Perrault: 1980, ‘Analyzing Intention in Utterances’.Artificial Intelligence 15, 143–178.Google Scholar
  2. Appelt, Douglas E. and Martha E. Pollack: 1992, ‘Weighted Abduction for Plan Ascription’.User Modeling and User-Adapted Interaction 2(1/2), 1–25 (this issue).Google Scholar
  3. Calistri-Yeh, Randall J.: 1991, ‘Utilizing User Models to Handle Ambiguity and Misconceptions in Robust Plan Recognition’.User Modeling and User-Adapted Interaction 1(4), 289–322.Google Scholar
  4. Carberry, Sandra: 1989, ‘Plan Recognition and Its Use in Understanding Dialogue’. In: Alfred Kobsa and Wolfgang Wahlster (eds.):User Models in Dialog Systems, Berlin: Springer Verlag.Google Scholar
  5. Carberry, Sandra: 1990a, ‘Incorporating Default Inferences Into Plan Recognition’. In:Proceedings of the Eighth National Conference on Artificial Intelligence, Boston, Massachusetts, pp. 471–478.Google Scholar
  6. Carberry, Sandra: 1990b,Plan Recognition in Natural Language Dialogue. Cambridge, MA: MIT Press.Google Scholar
  7. Carver, Norman F., Victor R. Lesser, and Daniel L. McCue: 1984, ‘Focusing in Plan Recognition’. In:Proceedings of the Fourth National Conference on Artificial Intelligence, Austin, Texas, pp. 42–48.Google Scholar
  8. Comrie, Bernard: 1981,Tense. Cambridge University Press, New York.Google Scholar
  9. Cohen, Philip R., C. Raymond Perrault, and James F. Allen: 1981, ‘Beyond Question Answering’. In: W. Lehnert and M. Ringle (eds.):Strategies for Natural Language Processing, Lawrence Erlbaum Associates, pp. 245–274.Google Scholar
  10. Cohen, Robin, Fei Song, Bruce Spencer, and Peter van Beek: 1991, ‘Exploiting Temporal and Novel Information from the User in Plan Recognition’.User Modeling and User-Adapted Interaction 1(2), 125–148.Google Scholar
  11. Eiselt, Kurt P.: 1987, ‘Recovering from Erroneous Inferences’.Proceedings of the Sixth National Conference on Artificial Intelligence, pp. 540–544.Google Scholar
  12. Goodman, Bradley A.: 1986a, ‘Miscommunication and Plan Recognition’. Presented at International Workshop on User Modeling, Maria Laach, West Germany.Google Scholar
  13. Goodman, Bradley A.: 1986b, ‘Reference Identification and Reference Identification Failures’.Computational Linguistics, pp. 273–305.Google Scholar
  14. Goodman, Bradley A. and Diane J. Litman: 1990, ‘Plan Rcognition for Intelligent Interfaces’. In:Proceedings of the Sixth Conference on Artificial Intelligence Applications, Santa Barbara, California, pp. 297–303.Google Scholar
  15. Goodman, Bradley A. and Diane J. Litman: 1992, ‘On the Interaction Between Plan Recognition and Intelligent Interfaces’.User Modeling and User-Adapted Interaction 2(1/2), 83–115 (this issue).Google Scholar
  16. Granger, Richard H.: 1981, ‘Directing and Re-directing Inference Pursuit: Extra-textual Influences on Text Interpretation’. In:Proceedings of the International Joint Conference on Artificial Intelligence, pp. 354–361.Google Scholar
  17. Konolige, Kurt and Martha Pollack: 1989, ‘Ascribing Plans to Agents: Preliminary Report’.Proceedings of the International Joint Conference on Artificial Intelligence, pp. 924–930.Google Scholar
  18. Litman, Diane: 1986, ‘Linguistic Coherence: A Plan-based Alternative’. In:Proceedings of the 24th Annual Meeting of the Association for Computational Linguistics, pp. 215–223.Google Scholar
  19. Litman, Diane and James Allen: 1987, ‘A Plan Recognition Model for Subdialogues in Conversation’.Cognitive Science 11, 163–200.Google Scholar
  20. Lochbaum, Karen, Barbara Grosz, and Candace Sidner: 1990, ‘Models of Plans to Support Communication: An Initial Report’. In:Proceedings of the Eighth National Conference on Artificial Intelligence, Boston, Massachusetts.Google Scholar
  21. Loui, R. P.: 1987, ‘Defeat Among Arguments: A System of Defeasible Inferences’.Computational Intelligence 3(2), 100–106.Google Scholar
  22. Mayfield, James: 1992, ‘Controlling Inference in Plan Recognition’.User Modeling and User-Adapted Interaction 2(1/2), 55–82 (this issue).Google Scholar
  23. McCawley, James D. 1981,Everything that Linguists have Always Wanted to Know about Logic But Were Ashamed to Ask. Chicago, IL: University of Chicago Press.Google Scholar
  24. Moens, Marc and Mark Steedman: 1988, ‘Temporal Ontology and Temporal Reference’.Computational Linguistics Special Issue on Tense 14(2).Google Scholar
  25. Norvig, P.: 1983, ‘Six Problems for Story Understanders’.Proceedings of the Third National Conference on Artificial Intelligence, pp. 284–287.Google Scholar
  26. O'Rorke, P.: 1983, ‘Reasons for Beliefs in Understanding: Applications of Non-monotonic Dependencies to Story Processing’.Proceedings of the Third National Conference on Artificial Intelligence, pp. 306–309.Google Scholar
  27. Pollack, M.: 1986a,Inferring Domain Plans in Question-Answering. PhD thesis, University of Pennsylvania, Philadelphia, Pennsylvania.Google Scholar
  28. Pollack, M.: 1986b, ‘A Model of Plan Inference that Distinguishes Between the Beliefs of Actors and Observers’. In:Proceedings of the 24th Annual Meeting of the Association for Computational Linguistics, New York, pp. 207–214.Google Scholar
  29. Pollack, M.: 1987, ‘Some Requirements for a Model of the Plan-inference Process in Conversation’. In: Ronan Reilly (ed.):Communication Failure in Dialogue, North Holland, pp. 245–256.Google Scholar
  30. Raskutti, Bhavani and Ingrid Zukerman: 1991, ‘Generation and Selection of Likely Interpretations During Plan Recognition in Task-oriented Consultation Systems’.User Modeling and User-Adapted Interaction 1(4), 323–353.Google Scholar
  31. Reichenbach, H.: 1947,Elements of Symbolic Logic. Macmillan Company, London, England.Google Scholar
  32. Retz-Schmidt, Gudula: 1991, ‘Recognizing Intentions, Interactions, and Causes of Plan Failures’.User Modeling and User-Adapted Interaction 1(2), 173–202.Google Scholar
  33. Sidner, Candace L.: 1983, ‘What the Speaker Means: The Recognition of Speakers' Plans in Discourse’.Computers and Mathematics With Applications 9(1), 71–82.Google Scholar
  34. Sidner, Candace L.: 1985, ‘Plan Parsing for Intended Response Recognition in Discourse’.Computational Intelligence 1, 1–10.Google Scholar
  35. Schmidt, C. F., N. S. Sridharan, and J. L. Goodson: 1978, ‘The Plan Recognition Problem: An Intersection of Psychology and Artificial Intelligence’.Artificial Intelligence 11, 45–82.Google Scholar
  36. Webber, Bonnie: 1988, ‘Introduction to Computational Linguistics Special Issue on Tense’.Computational Linguistics Special Issue on Tense 14(2).Google Scholar
  37. Wilensky, Robert: 1981, ‘Meta-planning: Representing and Using Knowledge About Planning in Problem Solving and Natural Language Understanding’.Cognitive Science 5, 197–233.Google Scholar
  38. Weischedel, Ralph M. and Norman K. Sondheimer: 1983, ‘Meta-rules AsaBasis for Processing Ill-formed Input’.American Journal of Computational Linguistics 9(3), 161–177.Google Scholar
  39. Wu, Dekai: 1991, ‘Active Acquisition of User Models: Implications for Decision-theoretic Dialog Planning and Plan Recognition’.User Modeling and User-Adapted Interaction 1(2), 149–172.Google Scholar

Copyright information

© Kluwer Academic Publishers 1992

Authors and Affiliations

  • Rhonda Eller
    • 1
  • Sandra Carberry
    • 1
  1. 1.Department of Computer and Information SciencesUniversity of DelawareNewarkUSA

Personalised recommendations