Advertisement

Rademacher Complexity and Grammar Induction Algorithms: What It May (Not) Tell Us

  • Sophia Katrenko
  • Menno van Zaanen
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6339)

Abstract

This paper revisits a problem of the evaluation of computational grammatical inference (GI) systems and discusses what role complexity measures can play for the assessment of GI. We provide a motivation for using the Rademacher complexity and give an example showing how this complexity measure can be used in practice.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bartlett, P.L., Mendelson, S.: Rademacher and gaussian complexities: Risk bounds and structural results. Journal of Machine Learning Research 3 (2002)Google Scholar
  2. 2.
    Bubeck, S., von Luxburg, U.: Nearest neighbor clustering: A baseline method for consistent clustering with arbitrary objective functions. JMLR 10, 657–698 (2009)MathSciNetGoogle Scholar
  3. 3.
    Clark, A.: Unsupervised Language Acquisition: Theory and Practice. PhD thesis, COGS, University of Sussex (2001)Google Scholar
  4. 4.
    van Zaanen, M., Adriaans, P.: Alignment-Based Learning versus EMILE: A Comparison. In: Proceedings of the Belgian-Dutch Conference on Artificial Intelligence (BNAIC), pp. 315–322 (2001)Google Scholar
  5. 5.
    van Zaanen, M., Geertzen, J.: Problems with evaluation of unsupervised empirical grammatical inference systems. In: Clark, A., Coste, F., Miclet, L. (eds.) ICGI 2008. LNCS (LNAI), vol. 5278, pp. 301–303. Springer, Heidelberg (2008)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Sophia Katrenko
    • 1
  • Menno van Zaanen
    • 2
  1. 1.Informatics InstituteUniversity of AmsterdamAmsterdamThe Netherlands
  2. 2.TiCCTilburg UniversityTilburgThe Netherlands

Personalised recommendations