Advertisement

On Dispersed and Choice Iteration in Incrementally Learnable Dependency Types

  • Denis Béchet
  • Alexandre Dikovsky
  • Annie Foret
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6736)

Abstract

We study learnability of Categorial Dependency Grammars (CDG), a family of categorial grammars expressing all kinds of projective, discontinuous and repeatable dependencies. For these grammars, it is known that they are not learnable from dependency structures.

We propose two different ways of modelling the repeatable dependencies through iterated types and the two corresponding families of CDG which cannot distinguish between the dependencies repeatable at least K times and those repeatable any number of times. For both we show that they are incrementally learnable in the limit from dependency structures.

Keywords

Grammatical inference Categorial grammar Dependency grammar Incremental learning Iterated types 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Angluin, D.: Inductive inference of formal languages from positive data. Information and Control 45, 117–135 (1980)MathSciNetCrossRefzbMATHGoogle Scholar
  2. 2.
    Béchet, D., Dikovsky, A., Foret, A.: Two models of learning iterated dependencies. In: Proc. of the 15th Conference on Formal Grammar (FG 2010), Copenhagen, Denmark. LNCS (2010) (to appear), http://www.angl.hu-berlin.de/FG10/fg10_list_of_papers
  3. 3.
    Béchet, D., Dikovsky, A., Foret, A., Moreau, E.: On learning discontinuous dependencies from positive data. In: Proc. of the 9th Intern. Conf. Formal Grammar (FG 2004), Nancy, France, pp. 1–16 (2004)Google Scholar
  4. 4.
    Buszkowski, W., Penn, G.: Categorial grammars determined from linguistic data by unification. Studia Logica 49, 431–454 (1990)MathSciNetCrossRefzbMATHGoogle Scholar
  5. 5.
    Dekhtyar, M., Dikovsky, A.: Generalized categorial dependency grammars. In: Avron, A., Dershowitz, N., Rabinovich, A. (eds.) Pillars of Computer Science. LNCS, vol. 4800, pp. 230–255. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  6. 6.
    Dekhtyar, M., Dikovsky, A., Karlov, B.: Iterated dependencies and kleene iteration. In: Proc. of the 15th Conference on Formal Grammar (FG 2010), Copenhagen, Denmark. LNCS (2010) (to appear), http://www.angl.hu-berlin.de/FG10/fg10_list_of_papers
  7. 7.
    Dikovsky, A.: Dependencies as categories. In: Recent Advances in Dependency Grammars, COLING 2004, pp. 90–97 (2004)Google Scholar
  8. 8.
    Dikovsky, A.: Multimodal categorial dependency grammars. In: Proc. of the 12th Conference on Formal Grammar, Dublin, Ireland, pp. 1–12 (2007)Google Scholar
  9. 9.
    Dikovsky, A.: Towards wide coverage categorial dependency grammars. In: Proc. of the ESSLLI 2009 Workshop on Parsing with Categorial Grammars. Book of Abstracts, Bordeaux, France (2009)Google Scholar
  10. 10.
    Gold, E.M.: Language identification in the limit. Information and Control 10, 447–474 (1967)MathSciNetCrossRefzbMATHGoogle Scholar
  11. 11.
    Kanazawa, M.: Learnable classes of categorial grammars. Studies in Logic, Language and Information, FoLLI & CSLI (1998)Google Scholar
  12. 12.
    Karlov, B.N.: Normal forms and automata for categorial dependency grammars. Vestnik Tverskogo Gosudarstvennogo Universiteta (Annals of Tver State University). Series: Applied Mathematics 35 (95), 23–43 (2008) (in russ.) Google Scholar
  13. 13.
    Mel’čuk, I.: Dependency Syntax. SUNY Press, Albany, NY (1988)Google Scholar
  14. 14.
    Shinohara, T.: Inductive inference of monotonic formal systems from positive data. New Generation Computing 8(4), 371–384 (1991)CrossRefzbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Denis Béchet
    • 1
  • Alexandre Dikovsky
    • 1
  • Annie Foret
    • 2
  1. 1.LINA UMR CNRS 6241Université de NantesFrance
  2. 2.IRISA, Université de Rennes 1France

Personalised recommendations