Evolving Natural Language Parser with Genetic Programming

  • Grzegorz Dulewicz
  • Olgierd Unold
Part of the Advances in Soft Computing book series (AINSC, volume 14)


When we try to deal with natural language processing (NLP) we have to start with a grammar of a natural language. But the grammars described in linguistic literature have an informal form and many exceptions. Thus, they are not useful to create final formal models of grammars, which make machine processing of sentences possible. These grammars can be a starting point for the attempts to create basic models of natural language grammar at the most. However, it requires expert knowledge. Machine learning based on a set of sample sentences can be the better way to find the grammar rules. This kind of learning allows to avoid the preparation of knowledge about the language for the NLP system. The examples of correct and incorrect sentences allow the NLP systems with the self-evolutionary parser to try to find the right grammar. This self-evolutionary parser can be improved on basis of new examples. Thus, the knowledge acquired in this way is flexible and easyly modifiable.


natural language processing genetic programming edge encoding 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Andre D, Bennet III F H, Koza J, Keane M, On the Theory of Designing Circuits using Genetic Programming and a Minimum of Domain Knowledge, Proc. of the 1998 IEEE Congress on Computional Intelligence WCCI’98, Anchorge, Alaska, 1998, pp. 130–135.Google Scholar
  2. Gruau F, Cellular encoding of genetic neural networks, Technical report 92–91, Ecole Normale Superieure de Lyon, Institut IMAG, 1992.Google Scholar
  3. Kandel A, Lee S C, Fuzzy Switching and Automata: Theory and Applications, Crane Russak, New York, 1979.Google Scholar
  4. Koza J, Genetic Programming, MIT Press, Cambridge, MA, 1992.zbMATHGoogle Scholar
  5. Koza J, Genetic programming II, MIT Press, Cambridge, MA, 1994.zbMATHGoogle Scholar
  6. Lankhorst M M, A Genetic Algorithm for the induction of Nondeterministic Pushdown Automata. Computing Science Reports CS-R 9502, Department of Computing Science, University of Groningen, 1995.Google Scholar
  7. Luke S, Spector L, Evolving Graphs and Networks with Edge Encoding: Preliminary Report. [in:] Koza J (eds.) Late-breaking Papers of Genetic Programming 96, Stanford Bookstore, 1996, pp. 117–124Google Scholar
  8. Roche E, Schabes Y, Finite-State Language Processing, A Bradford Book, The MIT Press, Cambridge, Massachusetts, 1997.Google Scholar
  9. Unold O, A Fuzzy Automaton Approach to Dialog Systems, Proc. of the IASTED International Conference-ASC’98, Cancun, Mexico, May 1998, pp. 215–218.Google Scholar
  10. Unold O, Application of Fuzzy Sets in Natural Language Processing, Proc. of the 6th Congress on Intelligent Techniques and Soft Computing EUFIT’98, Aachen, Germany, September 1998, pp. 1262–1266.Google Scholar
  11. Unold O, Toward fuzziness in natural language processing, [in:] Roy R at al [eds.] Advances in Soft Computing — Engineering Design and Manufacturing, Springer Verlag, London, 1999, pp. 554–567.Google Scholar
  12. Unold O, An evolutionary approach for the design of natural language parser. [in:] Suzuki Y at al [eds.] Soft Computing in Industrial Applications, Springer Verlag, London, 2000, pp. 293–297.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Grzegorz Dulewicz
    • 1
  • Olgierd Unold
    • 2
  1. 1.VICTOR Ltd.Poland
  2. 2.Institute of Engineering CyberneticsWroclaw University of TechnologyWroclawPoland

Personalised recommendations