Advertisement

A Genetic Programming Experiment in Natural Language Grammar Engineering

  • Marcin Junczys-Dowmunt
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7499)

Abstract

This paper describes an experiment in grammar engineering for a shallow syntactic parser using Genetic Programming and a treebank. The goal of the experiment is to improve the Parseval score of a previously manually created seed grammar. We illustrate the adaptation of the Genetic Programming paradigm to the problem of grammar engineering. The used genetic operators are described. The performance of the evolved grammar after 1,000 generations on an unseen test set is improved by 2.7 points F-score (3.7 points on the training set). Despite the large number of generations no overfitting effect is observed.

Keywords

Shallow parsing genetic programming natural language grammar engineering treebank 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Abney, S., Flickenger, S., Gdaniec, C., Grishman, C., Harrison, P., Hindle, D., Ingria, R., Jelinek, F., Klavans, J., Liberman, M., Marcus, M., Roukos, S., Santorini, B., Strzalkowski, T.: A Procedure for Quantitatively Comparing the Syntactic Coverage of English Grammars. In: Proceedings of a Workshop on Speech and Natural Language, San Francisco, pp. 306–311 (1991)Google Scholar
  2. 2.
    Koza, J.R.: The Genetic Programming Paradigm. In: Dynamic, Genetic, and Chaotic Programming, New York, pp. 203–321 (1992)Google Scholar
  3. 3.
    Poli, R., Langdon, W.B., McPhee, N.F.: A Field Guide to Genetic Programming (2008), http://www.gp-field-guide.org.uk
  4. 4.
    Dunay, B.D., Petry, F.E., Buckles, W.P.: Regular Language Induction with Genetic Programming. In: Proc. of the 1994 IEEE World Congress on Computational Intelligence, Orlando, pp. 396–400. IEEE Press (1994)Google Scholar
  5. 5.
    Keller, B., Lutz, R.: Learning Stochastic Context-Free Grammars from Corpora Using a Genetic Algorithm. University of Sussex (1997)Google Scholar
  6. 6.
    Smith, T.C., Witten, I.H.: A Genetic Algorithm for the Induction of Natural Language Grammars. In: Proc IJCAI 1995 Workshop on New Approaches to Learning for Natural Language Processing, pp. 17–24 (1995)Google Scholar
  7. 7.
    Korkmaz, E.E., Ucoluk, G.: Genetic Programming for Grammar Induction. In: 2001 Genetic and Evolutionary Computation Conference, San Francisco (2001)Google Scholar
  8. 8.
    Klein, D., Manning, C.D.: Accurate Unlexicalized Parsing. In: Proc. of the 41st Annual Meeting of the Association for Computational Linguistics, pp. 423–430 (2003)Google Scholar
  9. 9.
    Kübler, S., Hinrichs, E.W., Maier, W.: Is it really that difficult to parse German. In: Proc. of the Conference on Empirical Methods in Natural Language Processing, pp. 111–119 (2006)Google Scholar
  10. 10.
    Graliński, F., Jassem, K., Junczys-Dowmunt, M.: PSI-toolkit: A Natural Language Processing Pipeline. In: To appear in: Computational Linguistics — Applications. SCI. SpringerGoogle Scholar
  11. 11.
    Przepiórkowski, A., Buczyński, A.: \(\spadesuit\): Shallow parsing and disambiguation engine. In: Proceedings of the 3rd Language & Technology Conference, Poznań (2007)Google Scholar
  12. 12.
    Junczys-Dowmunt, M.: It’s all about the Trees — Towards a Hybrid Syntax-Based MT System. In: Proceedings of IMCSIT, pp. 219–226 (2009)Google Scholar
  13. 13.
    Abeillé, A., Clément, L., Toussenel, F.: Building a Treebank for French. In: Treebanks: Building and Using Parsed Corpora, pp. 165–188. Springer (2003)Google Scholar
  14. 14.
    Crane, E.F., McPhee, N.F.: The Effects of Size and Depth limits on Tree Based Genetic Programming. In: Genetic Programming Theory and Practice III, pp. 223–240. Springer (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Marcin Junczys-Dowmunt
    • 1
  1. 1.Faculty of Mathematics and Computer ScienceAdam Mickiewicz UniversityPoznańPoland

Personalised recommendations