Language learning without overgeneralization

  • Shyam Kapur
  • Gianfranco Bilardi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 577)


Language learnability is investigated in the Gold paradigm of inductive inference from positive data. Angluin gave a characterization of learnable families in this framework. Here, learnability of families of recursive languages is studied when the learner obeys certain natural constraints. Exactly learnable families are characterized for prudent learners with the following types of constraints: (0) conservative, (1) conservative and consistent, (2) conservative and responsive, and (3) conservative, consistent and responsive. The class of learnable families is shown to strictly increase going from (3) to (2) and from (2) to (1), while it stays the same going from (1) to (0). It is also shown that, when exactness is not required, prudence, consistency and responsiveness, even together, do not restrict the power of conservative learners.


Turing Machine Inductive Inference Positive Data Total Index Partial Recursive Function 
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. [Ang80a]
    Dana Angluin. Finding patterns common to a set of strings. Journal of Computer System Sciences, 21:46–62, 1980.Google Scholar
  2. [Ang80b]
    Dana Angluin. Inductive inference of formal languages from positive data. Information and Control, 48:117–135, 1980.Google Scholar
  3. [Ber85]
    Robert Berwick. The Acquisition of Syntactic Knowledge. MIT press, Cambridge, MA, 1985.Google Scholar
  4. [Ful90]
    Mark A. Fulk. Prudence and other conditions on formal language learning. Information and Computation, 85:1–11, 1990.Google Scholar
  5. [Gol67]
    E. M. Gold. Language identification in the limit. Information and Control, 10:447–474, 1967.Google Scholar
  6. [Kap91]
    Shyam Kapur. Computational Learning of Languages. Technical Report 91-1234, Cornell University, Ithaca, NY, September 1991. Ph.D. Thesis.Google Scholar
  7. [MW84]
    Irene Mazurkewich and Lydia White. The acquisition of dative-alternation: unlearning overgeneralizations. Cognition, 16(3):261–283, 1984.Google Scholar
  8. [OSW82]
    Daniel N. Osherson, Michael Stob, and Scott Weinstein. Learning strategies. Information and Control, 53:32–51, 1982.Google Scholar
  9. [OSW86]
    Daniel N. Osherson, Michael Stob, and Scott Weinstein. Systems that Learn: An Introduction to Learning. MIT press, Cambridge, MA, 1986.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1992

Authors and Affiliations

  • Shyam Kapur
    • 1
  • Gianfranco Bilardi
    • 2
    • 3
  1. 1.Institute for Research in Cognitive ScienceUniversity of PennsylvaniaPhiladelphiaUSA
  2. 2.Department of Computer ScienceCornell UniversityIthacaUSA
  3. 3.Dipartimento di Elettronica ed InformaticaUniversitā di PadovaPadovaItaly

Personalised recommendations