PAC Learning of Some Subclasses of Context-Free Grammars with Basic Distributional Properties from Positive Data

  • Chihiro Shibata
  • Ryo Yoshinaka
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8139)


In recent years different interesting subclasses of cfls have been found to be learnable by techniques generically called distributional learning. The theoretical study on the exact learning of cfls by those techniques under different learning scheme is now quite mature. On the other hand, positive results on the pac learnability of cfls are rather limited and quite weak. This paper shows that several subclasses of context-free languages that are known to be exactly learnable with membership queries by distributional learning techniques are pac learnable from positive data under some assumptions on the string distribution.


Regular Language Positive Data Probabilistic Learning Membership Query Nonterminal Symbol 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Angluin, D.: Learning regular sets from queries and counterexamples. Information and Computation 75(2), 87–106 (1987)MathSciNetCrossRefzbMATHGoogle Scholar
  2. 2.
    Clark, A.: PAC-learning unambiguous NTS languages. In: Sakakibara, Y., Kobayashi, S., Sato, K., Nishino, T., Tomita, E. (eds.) ICGI 2006. LNCS (LNAI), vol. 4201, pp. 59–71. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  3. 3.
    Clark, A.: A learnable representation for syntax using residuated lattices. In: Proceedings of the 14th Conference on Formal Grammar, Bordeaux, France (2009)Google Scholar
  4. 4.
    Clark, A.: Distributional learning of some context-free languages with a minimally adequate teacher. In: Sempere, García (eds.) [12], pp. 24–37Google Scholar
  5. 5.
    Clark, A.: Learning context free grammars with the syntactic concept lattice. In: Sempere, García (eds.) [12], pp. 38–51Google Scholar
  6. 6.
    Clark, A., Coste, F., Miclet, L. (eds.): ICGI 2008. LNCS (LNAI), vol. 5278. Springer, Heidelberg (2008)Google Scholar
  7. 7.
    Clark, A., Eyraud, R.: Polynomial identification in the limit of substitutable context-free languages. Journal of Machine Learning Research 8, 1725–1745 (2007)MathSciNetzbMATHGoogle Scholar
  8. 8.
    Clark, A., Eyraud, R., Habrard, A.: A note on contextual binary feature grammars. In: EACL 2009 workshop on Computational Linguistic Aspects of Grammatical Inference, pp. 33–40 (2009)Google Scholar
  9. 9.
    Clark, A., Thollard, F.: Partially distribution-free learning of regular languages from positive samples. In: COLING (2004)Google Scholar
  10. 10.
    Dubhashi, D., Ranjan, D.: Balls and bins: A study in negative dependence. Random Structures and Algorithms 13(2), 99–124 (1998)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Luque, F.M., López, G.G.I.: PAC-learning unambiguous k,l-NTS ≤  languages. In: Sempere, García (eds.) [12], pp. 122–134Google Scholar
  12. 12.
    Sempere, J.M., García, P. (eds.): ICGI 2010. LNCS, vol. 6339. Springer, Heidelberg (2010)Google Scholar
  13. 13.
    Shirakawa, H., Yokomori, T.: Polynomial-time MAT learning of c-deterministic context-free grammars. Transaction of Information Processing Society of Japan 34, 380–390 (1993)Google Scholar
  14. 14.
    Tajima, Y., Kotani, Y.: Polynomial time probabilistic learning of a subclass of linear languages with queries. In: Clark, et al. [6], pp. 187–199Google Scholar
  15. 15.
    Yoshinaka, R.: Identification in the limit of k,l-substitutable context-free languages. In: Clark, et al. [6], pp. 266–279Google Scholar
  16. 16.
    Yoshinaka, R.: Towards dual approaches for learning context-free grammars based on syntactic concept lattices. In: Mauri, G., Leporati, A. (eds.) DLT 2011. LNCS, vol. 6795, pp. 429–440. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  17. 17.
    Yoshinaka, R.: Integration of the dual approaches in the distributional learning of context-free grammars. In: Dediu, A.-H., Martín-Vide, C. (eds.) LATA 2012. LNCS, vol. 7183, pp. 538–550. Springer, Heidelberg (2012)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Chihiro Shibata
    • 1
  • Ryo Yoshinaka
    • 2
  1. 1.School of Computer ScienceTokyo University of TechnologyJapan
  2. 2.Graduate School of InformaticsKyoto UniversityJapan

Personalised recommendations