Advertisement

Representational issues for context free grammar induction using genetic algorithms

  • Peter Wyard
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 862)

Abstract

This paper describes results on the inference of two classes of context free grammar (CFG), using a genetic algorithm (GA). The first class is that of n-symbol palindromes, where n=2 to 4; the second class is small natural language grammars. The use of different normal forms of the grammars was compared experimentally. The use of different encodings of the grammars in the chromosomes of the GA, and the implications of these different representations within the genetic search are discussed. It is concluded that by paying attention to representational issues, worthwhile results may be achieved using a GA.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Fu, K, and Booth, T, Grammatical Inference: Introduction and Survey, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 8, pp. 343–375, 1986.Google Scholar
  2. [2]
    Gold, E.M., Complexity of automaton identification from given data, Information and Control, 37, 302–320.Google Scholar
  3. [3]
    Angluin, D., and Smith, C.H., “Inductive inference: theory and methods”. Computing Surveys, vol. 15, no.3, September 1983.Google Scholar
  4. [4]
    Cohen, P.R., and Feigenbaum, E.A., “The handbook of artificial intelligence: volume 2”. Los Altos, California. Publ Morgan Kaufmann, 1983.Google Scholar
  5. [5]
    Lucas,S, New Directions in Grammatical Inference, Proc. IEE Colloq. on Grammatical Inference: Theory, Applications and Alternatives, 1993, Digest No. 1993/092, London.Google Scholar
  6. [6]
    Holland, J.H. “Adaptation in natural and artificial systems”, Univ. of Michigan Press, Ann Arbor, 1975.Google Scholar
  7. [7]
    Goldberg, D., Genetic Algorithms in Search, Optimization and Machine Learning, Addison-Wesley, 1989.Google Scholar
  8. [8]
    Lucas, S, Biased Chromosomes for Grammatical Inference, Proc. of Natural Algorithms in Signal Processing, IEE Workshop at Danbury Park, UK, 1993.Google Scholar
  9. [9]
    Lucas,S, Structuring Chromosomes for Context-Free Grammar Evolution, First International Conference on Evolutionary Computing, pp. 130–135, 1994.Google Scholar
  10. [10]
    Kitano, H, Designing neural networks using genetic algorithm with graph generation system, Complex Systems, vol. 4, pp. 461–476, 1990.Google Scholar
  11. [11]
    Gruau, F, Cellular Encoding as a Graph Grammar, Proc. IEE Colloq. on Grammatical Inference: Theory, Applications and Alternatives, 1993, Digest No. 1993/092, London.Google Scholar
  12. [12]
    Koza, J, Genetic Programming, MIT Press, 1992.Google Scholar
  13. [13]
    Wyard, P J, Context Free Grammar Induction Using Genetic Algorithms, Proc. IEE Colloq. on Grammatical Inference: Theory, Applications and Alternatives, 1993, Digest No. 1993/092, London.Google Scholar
  14. [14]
    Giordano, J-Y, Version Space for Learning Context-Free Grammars, Proc. IEE Colloq. on Grammatical Inference: Theory, Applications and Alternatives, 1993, Digest No. 1993/092, London.Google Scholar
  15. [15]
    Lari, K. and Young, S.J., The estimation of stochastic context-free grammars using the Inside-Outside algorithm, Computer Speech and Language, vol. 4, no. 1, 1990.Google Scholar
  16. [16]
    Hopcroft, J. and Ullman, J, Introduction to Automata Theory, Languages and Computation, Addison-Wesley, 1979.Google Scholar
  17. [17]
    Dunay,D, Petry, F, and Buckles, B, Regular Language Induction with Genetic Programming, First International Conference on Evolutionary Computing, pp. 396–400, 1994.Google Scholar
  18. [18]
    Goldberg, D, Genetic Algorithms in Search, Optimization and Machine Learning, Addison-Wesley, 1989.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1994

Authors and Affiliations

  • Peter Wyard
    • 1
  1. 1.Natural Language Group, Systems Research DivisionBT Laboratories, Martlesham HeathIpswichUK

Personalised recommendations