A hierarchy of language families learnable by regular language learners

  • Yuji Takada
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 862)


We shall establish the existence of a hierarchy of language families, in which the learning problem for each family is reduced to the learning problem for regular languages. Thus this boosts the learnability of learning algorithms for regular languages.


Learning from examples hierarchy of language families even linear grammars regular languages control sets 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [Ang87]
    Dana Angluin. Learning regular sets from queries and counter-examples. Information and Computation, 75:87–106, 1987.CrossRefGoogle Scholar
  2. [AP64]
    V. Amar and G. Putzolu. On a family of linear grammars. Information and Control, 7:283–291, 1964.CrossRefGoogle Scholar
  3. [Kha74]
    Nabil A. Khabbaz. A geometric hierarchy of languages. Journal of Computer and System Sciences, 8:142–157, 1974.Google Scholar
  4. [OG92]
    José Oncina and Pedro García. Identifying regular languages in polynomial time. In H. Bunke, editor, Advances in structural and syntactic pattern recognition, pages 99–108. World Scientific, Singapore, 1992.Google Scholar
  5. [RN88]
    V. Radhakrishnan and G. Nagaraja. Inference of even linear grammars and its application to picture description languages. Pattern Recognition, 21(1):55–62, 1988.Google Scholar
  6. [Sal73]
    Arto Salomaa. Formal Languages. Academic Press, New York, 1973.Google Scholar
  7. [Tak88]
    Yuji Takada. Grammatical inference for even linear languages based on control sets. Information Processing Letters, 28(4):193–199, 1988.Google Scholar
  8. [Tak92]
    Yuji Takada. Algorithmic Learning Theory of Formal Languages and its Applications. Doctoral thesis, Hokkaido University, 1992. Also published as IIAS Research Report RR-93-6E.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1994

Authors and Affiliations

  • Yuji Takada
    • 1
  1. 1.Institute for Social Information Science (ISIS)Fujitsu Laboratories LtdShizuokaJapan

Personalised recommendations