PAC-Learning Unambiguous NTS Languages

  • Alexander Clark
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4201)


Non-terminally separated (NTS) languages are a subclass of deterministic context free languages where there is a stable relationship between the substrings of the language and the non-terminals of the grammar. We show that when the distribution of samples is generated by a PCFG, based on the same grammar as the target language, the class of unambiguous NTS languages is PAC-learnable from positive data alone, with polynomial bounds on data and computation.


Target Language Regular Language Context Free Grammar Context Free Language Categorial Grammar 
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. [Adr99]
    Adriaans, P.: Learning shallow context-free languages under simple distributions. Technical Report ILLC Report PP-1999-13, Institute for Logic, Language and Computation, Amsterdam (1999)Google Scholar
  2. [BS85]
    Boasson, L., Senizergues, S.: NTS languages are deterministic and congruential. J. Comput. Syst. Sci. 31(3), 332–342 (1985)MATHCrossRefMathSciNetGoogle Scholar
  3. [CE05]
    Clark, A., Eyraud, R.: Identification in the limit of substitutable context free languages. In: Jain, S., Simon, H.U., Tomita, E. (eds.) ALT 2005. LNCS (LNAI), vol. 3734, pp. 283–296. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  4. [Cha01]
    Charniak, E.: Immediate head parsing for language models. In: Proceedings of the 39th annual meeting of the ACL, Toulouse, France, pp. 116–123 (2001)Google Scholar
  5. [Cla06]
    Clark, A.: Learning deterministic context free grammars in the Omphalos competition. Machine Learning (to appear, 2006)Google Scholar
  6. [CT04a]
    Clark, A., Thollard, F.: PAC-learnability of probabilistic deterministic finite state automata. Journal of Machine Learning Research 5, 473–497 (2004)MathSciNetGoogle Scholar
  7. [CT04b]
    Clark, A., Thollard, F.: Partially distribution-free learning of regular languages from positive samples. In: Proceedings of COLING, Geneva, Switzerland (2004)Google Scholar
  8. [DR98]
    Dubhashi, D.P., Ranjan, D.: Balls and bins: A study in negative dependence. Random Structures and Algorithms 13(2), 99–124 (1998)MATHCrossRefMathSciNetGoogle Scholar
  9. [Har54]
    Harris, Z.: Distributional structure. Word 10(2-3), 146–162 (1954)Google Scholar
  10. [JC00]
    Jelinek, F., Chelba, C.: Structured language modeling for speech recognition. Computer, Speech and Language 14(4), 283–332 (2000)CrossRefGoogle Scholar
  11. [KMR+94]
    Kearns, M.J., Mansour, Y., Ron, D., Rubinfeld, R., Schapire, R.E., Sellie, L.: On the learnability of discrete distributions. In: Proc. of the 25th Annual ACM Symposium on Theory of Computing, pp. 273–282 (1994)Google Scholar
  12. [RST98]
    Ron, D., Singer, Y., Tishby, N.: On the learnability and usage of acyclic probabilistic finite automata. J. Comput. Syst. Sci. 56(2), 133–152 (1998)MATHCrossRefMathSciNetGoogle Scholar
  13. [Sen85]
    Senizergues, G.: The equivalence and inclusion problems for NTS languages. J. Comput. Syst. Sci. 31(3), 303–331 (1985)MATHCrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Alexander Clark
    • 1
  1. 1.Department of Computer ScienceRoyal Holloway University of LondonEgham, Surrey

Personalised recommendations