Advertisement

Grammar model and grammar induction in the system NL PAGE

  • Vlado Kešelj
Conference paper
  • 90 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1433)

Abstract

The input to the natural language parser generation system NL PAGE is in the form of an annotated natural language text, which is used to generate a grammar and a lexicon. This paper describes the format of the text, a new grammar model that is used in the system, and the process of grammar induction.

Keywords

Parse Tree Grammar Rule Grammar Formalism Attribute Grammar NATO Advance Study Institute 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    C. H. A. Koster. Affix grammars for natural languages. In Attribute Grammars, Applications and Systems, International Summer School SAGA, Prague, Czechoslovakia, volume 545 of Lecture Notes in Computer Science. Springer-Verlag, June 1991.Google Scholar
  2. 2.
    F. Jelinek, J. D. Lafferty, and R. Mercer. Basic methods of probabilistic context-free grammars. In Speech Recognition and Understanding: Recent Advances, Trends, and Applications. Proceedings of the NATO Advanced Study Institute, pages 345–360, 1992.Google Scholar
  3. 3.
    Christer Samuelsson, Pasi Tapanainen, and Atro Voutilainene. Inducing constraint grammars. In Third International Colloquium, ICGI-96, pages 146–155, September 1996.Google Scholar
  4. 4.
    David M. Magerman. Learning grammatical structure using statistical decision-trees. In Third International Colloquium, ICGI-96, pages 1–21, September 1996.Google Scholar
  5. 5.
    Vlado Kešelj. Multi-agent systems for Internet information retrieval using natural language processing. Master's thesis, University of Waterloo, 1997.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Vlado Kešelj
    • 1
  1. 1.Department of Computer ScienceUniversity of WaterlooWaterlooCanada

Personalised recommendations