Advertisement

Overcoming Limitations of Rule-Based Systems: An Example of a Hybrid Deterministic Parser

  • Stan C. Kwasny
  • Kanaan A. Faisal
Conference paper
Part of the Informatik-Fachberichte book series (INFORMATIK, volume 252)

Abstract

The rule-based approach to building intelligent systems is prevalent throughout the enterprise of Artificial Intelligence. Many famous systems have succeeded because they rely on rules at least to some extent. Through good knowledge engineering, the representation and encodement of the elements required to find adequate problem solutions can be facilitated. But despite enormous efforts, rule-based systems are far from perfect in their performance. What are the limitations and how can they be overcome?

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Mitchell P. Marcus, A Theory of Syntactic Recognition for Natural Language, MIT Press, Cambridge, MA, 1980.zbMATHGoogle Scholar
  2. 2.
    Randall Davis, “Amplifying Expertise with Expert Systems,” in The AI Business: Commercial Uses of Artificial Intelligence, ed. P.H. Winston and K.A. Prendergast, MIT Press, Cambridge, MA, 1984.Google Scholar
  3. 3.
    Randall Davis, “Teiresias: Applications of Meta-Level Knowledge,” in Knowledge-Based Systems in Artificial Intelligence, ed. R. Davis and D.B. Lenat, McGraw-Hill, New York, NY, 1982.Google Scholar
  4. 4.
    M.F. St. John and J.L. McClelland, “Learning and Applying Contextual Constraints in Sentence Comprehension,” Technical Report AIP-39, Department of Psychology, Carnegie-Mellon University, Pittsburgh, PA, June 8, 1988.Google Scholar
  5. 5.
    E. Collins, S. Ghosh, and C.L. Scofield, “An Application of a Multiple Neural Network Learning System to Emulation of Mortgage Underwriting Judgements,” in Proceedings of IEEE International Confernce on Neural Networks II, pp. 459–466, 1988.CrossRefGoogle Scholar
  6. 6.
    Kanaan A. Faisal and Stan C. Kwasny, “Deductive and Inductive Learning in a Connectionist Deterministic Parser,” in Proceedings of the International Joint Conference on Neural Networks, vol. 2, pp. 471–474, Lawrence Erlbaum Associates, Hillsdale, NJ, January 15–19, 1990.Google Scholar
  7. 7.
    Kanaan A. Faisal and Stan C. Kwasny, “Design of a Hybrid Deterministic Parser,” in Proceedings of the 13th International Conference on Computational Linguistics, Helsinki, Finland, August, 1990. ( FORTHCOMING )Google Scholar
  8. 8.
    Stan C. Kwasny and Kanaan A. Faisal, Connectionism and Determinism in a Syntactic Parser, Connection Science: Journal of Neural Comuting, Artificial Intelligence, and Cognitive Research — Special Issue on Connectionist Research on Natural Language, Carfax Publishing Company, Abingdon, Oxfordshire, England, 1990. (in press)Google Scholar
  9. 9.
    Eugene Charniak, “A Parser with Something for Everyone,” in Parsing Natural Language, ed. M. King, pp. 117–150, Academic Press, New York, NY, 1983.Google Scholar
  10. 10.
    Robert Milne, “Resolving Lexical Ambiguity in a Deterministic Parser,” Computational Linguistics, vol. 12, no. 1, pp. 1–12, January-March, 1986.Google Scholar
  11. 11.
    Robert C. Berwick, The Acquisition of Syntactic Knowledge, MIT Press, Cambridge, MA, 1985.Google Scholar
  12. 12.
    David E. Rumelhart, Geoffrey Hinton, and Ronald J. Williams, “Learning Internal Representations by Error Propagation,” in Parallel Distributed Processing, ed. D.E. Rumelhart and J.L. McClelland, pp. 318–364, MIT Press, Cambridge, MA, 1986.Google Scholar
  13. 13.
    Patrick H. Winston, Artificial Intelligence, Addison-Wesley, Reading, Ma, 1984.zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1990

Authors and Affiliations

  • Stan C. Kwasny
    • 1
  • Kanaan A. Faisal
    • 2
  1. 1.Center for Intelligent Computer SystemsWashington UniversitySt. LouisUSA
  2. 2.Information and Computer Science DepartmentKing Fand University of Petroleum and MineralsDhahranKingdom of Saudi Arabia

Personalised recommendations