Abstract
Most Natural Language Generation systems developed to date assume that a user will learn only what is explicitly stated in the discourse. This assumption leads to the generation of discourse that states explicitly all the information to be conveyed, and does not address further inferences from the discourse. In this paper, we describe a student model which provides a qualitative representation of a student's beliefs and inferences, and a content planning mechanism which consults this model in order to address the above problems. Our mechanism performs inferences in backward reasoning mode to generate discourse that conveys the intended information, and in forward reasoning mode to draw conclusions from the presented information. The forward inferences enable our mechanism to address possible incorrect inferences from the discourse, and to omit information that may be easily inferred from the discourse. In addition, our mechanism improves the conciseness of the generated discourse by omitting information known by the student. The domain of our implementation is the explanation of concepts in high school algebra.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Appelt, D.E.: 1982, ‘Planning Natural Language Utterances to Satisfy Multiple Goals’. Technical Note 259, SRI International, March 1982.
Bonarini A., E. Cappelletti and A. Corrao: 1990, ‘Network-based Management of Subjective Judgments: A Proposal Accepting Cyclic Dependencies’. Report No. 90-067, Department of Electronics, Politecnico di Milano.
Buchanan, B. and E. Shortliffe: 1985,Rule-based Expert Systems: The MYCIN Experiments of the Stanford Heuristic Programming Project, Addison-Wesley.
Burton, R.R.: 1982, ‘Diagnosing Bugs in a Simple Procedural Skill’. In: D. Sleeman and J.S. Brown (eds.),Intelligent Tutoring Systems, London: Academic Press, pp. 157–183.
Carberry, S.: 1988, ‘Modeling the User's Plans and Goals’.Computational Linguistics 14 (3), 23–37.
Cawsey, A.: 1990, ‘Generating Explanatory Discourse’. In: R. Dale, C. Mellish and M. Zock (eds.),Current Research in Natural Language Generation, Academic Press, pp. 75–102.
Cawsey, A.: 1991, ‘Using Plausible Inference Rules in Description Planning’. In:Proceedings of the Fifth Conference of the European Chapter of the ACL.
Clark, D.A.: 1990, ‘Numerical and Symbolic Approaches to Uncertainty Management in AI’Artificial Intelligence Review 4, 109–146.
Dale, R.: 1990, ‘Generating Recipes: An Overview of Epicure’. In: R. Dale, C. Mellish and M. Zock (eds.),Current Research in Natural Language Generation, Academic Press, pp. 229–255.
Driankov, D.: 1986, ‘Towards a Many-Valued Logic of Quantified Belief’. Doctoral Dissertation, Department of Computer and Information Science, Linköping University, Sweden.
Dyer, M.G.: 1983,In-Depth Computer Understanding: A Computer Model of Integrated Processing for Narrative Comprehension, MIT Press, Cambridge, Massachusetts.
Green, N. and S. Carberry: 1992, ‘Conversational Implicatures in Indirect Replies’. In:Proceedings of the Thirtieth Annual Meeting of the Association for Computational Linguistics, Newark, Delaware, pp. 64–71.
Grice, H.P.: 1975, ‘Logic and Conversation’. In: P.J. Cole and J.L. Morgan (eds.),Syntax and Semantics, Volume 3: Speech Acts, Academic Press, pp. 41–58.
Grice, H.P.: 1978, ‘Further Notes on Logic and Conversation’. In: P.J. Cole and J.L. Morgan (eds.),Syntax and Semantics, Volume 9: Pragmatics, Academic Press.
Hirschberg, J.B.: 1985, ‘A Theory of Scalar Implicature’. Doctoral Dissertation, The Moore School of Electrical Engineering, University of Pennsylvania, Philadelphia, Pennsylvania.
Horacek, H.: 1991, ‘Exploiting Conversational Implicature for Generating Concise Explanations’. In:Proceedings of the Meeting of the European Association of Computational Linguistics.
Hovy, E.H.: 1988, ‘Planning Coherent Multisentential Text’. In:Proceedings of the Twenty-Sixth Annual Meeting of the Association for Computational Linguistics, Buffalo, New York, pp. 163–169.
Joshi, A., B.L. Webber and R.M. Weischedel: 1984, ‘Living Up to Expectations: Computing Expert Responses’. In:AAAI-84, Proceedings of the National Conference on Artificial Intelligence, Austin, Texas, pp. 169–175.
Lascarides, A. and J. Oberlander: 1992, Abducing Temporal Discourse. In: R. Dale, E. Hovy, D. Rösner and O. Stock (eds.),Aspects of Automated Language Generation, Springer-Verlag, Berlin, Heidelberg, pp. 167–182.
Litman, D. and J.F. Allen: 1987, ‘A Plan Recognition Model for Subdialogues in Conversation’. In:Cognitive Science 11, 163–200.
Matz, M.: 1982, ‘Towards a Process Model for High School Algebra Errors’. In: D. Sleeman and J.S. Brown (eds.),Intelligent Tutoring Systems, London: Academic Press, pp. 25–50.
Maybury, M.T.: 1990, ‘Custom Explanations: Exploiting User Models to Plan Multisentential Text’. In:Proceedings of the Second International Workshop on User Modeling, Honolulu, Hawaii.
McKeown, K.R.: 1985, ‘Discourse Strategies for Generating Natural Language Text’.Artificial Intelligence 27, 1–41.
Meteer, M.: 1991, ‘Bridging the Generation Gap between Text Planning and Linguistic Realization’.Computational Intelligence 7 (4), Special Issue on Natural Language Generation, 296–304.
Moore, J.D.: 1989, ‘A Reactive Approach to Explanation in Expert and Advice-Giving Systems’. Doctoral Dissertation, Department of Computer Science, University of California, Los Angeles, California.
Moore, J.D. and C.L. Paris: 1992, ‘Feedback to Compensate for the Unreliability of User Models’. In:User Modeling and User-Adapted Interaction 2 (4), 287–330.
Moore, J.D. and W. Swartout: 1989, ‘A Reactive Approach to Explanation’. In:Proceedings of the Eleventh International Joint Conference on Artificial Intelligence, Detroit, Michigan, pp. 1504–1510.
Norvig, P.: 1989, ‘Marker Passing as a Weak Method for Text Inferencing’. In:Cognitive Science 13, 569–620.
Paris, C.L.: 1988, ‘Tailoring Object Descriptions to a User's Level of Expertise’. In:Computational Linguistics 14 (3), 64–78.
Reiter, E.: 1990, ‘Generating Descriptions that Exploit a User's Domain Knowledge’. In: R. Dale, C. Mellish and M. Zock (eds.),Current Research in Natural Language Generation, Academic Press, pp. 257–285.
Sleeman, D.: 1982, ‘Inferring (mal) Rules from Pupil's Protocols’. In:ECAI-82, Proceedings of the European Artificial Intelligence Conference, pp. 160–164.
Sleeman, D.: 1984, ‘Mis-Generalization: An Explanation of Observed Mal-rules’. In:Proceedings of the Sixth Annual Conference of the Cognitive Science Society, Boulder, Colorado, pp. 51–56.
Suthers, D.: 1991, ‘A Task-appropriate Hybrid Architecture for Explanation’. In:Computational Intelligence 7 (4), Special Issue on Natural Language Generation, 315–333.
van Beek, P.: 1987, ‘A Model for Generating Better Explanations’. In:Proceedings of the Twenty-Fifth Annual Meeting of the Association for Computational Linguistics, Stanford, California, pp. 215–220.
van Lehn, K.: 1983, ‘Human Procedural Skill Acquisition: Theory, Model and Psychological Validation’. In:AAAI-83, Proceedings of the National Conference on Artificial Intelligence, Washington, D.C., pp. 420–423.
Zukerman, I.: 1990a, ‘A Predictive Approach for the Generation of Rhetorical Devices’. In:Computational Intelligence 6 (1), 25–40.
Zukerman, I.: 1990b, ‘Consulting a Shallow Model of a Listener to Generate Supportive Rhetorical Devices’. In:Proceedings of the Second International Workshop on User Modelin, Honolulu, Hawaii.
Zukerman, I.: 1991, ‘Using Meta Comments to Generate Fluent Text in a Technical Domain’.Computational Intelligence 7 (4), Special Issue on Natural Language Generation, 276–295.
Zukerman, I., and R. McConachy: 1993, ‘An Optimizing Method for Structuring Inferentially Linked Discourse’. In:AAAI-93, Proceedings of the National Conference on Artificial Intelligence, Washington, D.C., 202–207.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Zukerman, I., Mcconachy, R. Consulting a user model to address a user's inferences during content planning. User Model User-Adap Inter 3, 155–185 (1993). https://doi.org/10.1007/BF01099728
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF01099728