Skip to main content
SpringerLink
Log in
SpringerLink
Log in

Language learning without overgeneralization

  • Conference paper
  • First Online:
STACS 92 (STACS 1992)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 577))

Included in the following conference series:

Abstract

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.

This work was supported in part by the National Science Foundation grant MIP-86-02256.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Dana Angluin. Finding patterns common to a set of strings. Journal of Computer System Sciences, 21:46–62, 1980.

    Google Scholar 

  2. Dana Angluin. Inductive inference of formal languages from positive data. Information and Control, 48:117–135, 1980.

    Google Scholar 

  3. Robert Berwick. The Acquisition of Syntactic Knowledge. MIT press, Cambridge, MA, 1985.

    Google Scholar 

  4. Mark A. Fulk. Prudence and other conditions on formal language learning. Information and Computation, 85:1–11, 1990.

    Google Scholar 

  5. E. M. Gold. Language identification in the limit. Information and Control, 10:447–474, 1967.

    Google Scholar 

  6. Shyam Kapur. Computational Learning of Languages. Technical Report 91-1234, Cornell University, Ithaca, NY, September 1991. Ph.D. Thesis.

    Google Scholar 

  7. Irene Mazurkewich and Lydia White. The acquisition of dative-alternation: unlearning overgeneralizations. Cognition, 16(3):261–283, 1984.

    Google Scholar 

  8. Daniel N. Osherson, Michael Stob, and Scott Weinstein. Learning strategies. Information and Control, 53:32–51, 1982.

    Google Scholar 

  9. Daniel N. Osherson, Michael Stob, and Scott Weinstein. Systems that Learn: An Introduction to Learning. MIT press, Cambridge, MA, 1986.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institute for Research in Cognitive Science, University of Pennsylvania, 3401 Walnut Street-Suite C, 19104, Philadelphia, PA, USA

    Shyam Kapur

  2. Department of Computer Science, Cornell University, 14853, Ithaca, New York, USA

    Gianfranco Bilardi

  3. Dipartimento di Elettronica ed Informatica, Universitā di Padova, 35131, Padova, Italy

    Gianfranco Bilardi

Authors
  1. Shyam Kapur
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Gianfranco Bilardi
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Alain Finkel Matthias Jantzen

Rights and permissions

Reprints and permissions

Copyright information

© 1992 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Kapur, S., Bilardi, G. (1992). Language learning without overgeneralization. In: Finkel, A., Jantzen, M. (eds) STACS 92. STACS 1992. Lecture Notes in Computer Science, vol 577. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-55210-3_188

Download citation

  • DOI: https://doi.org/10.1007/3-540-55210-3_188

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-55210-9

  • Online ISBN: 978-3-540-46775-5

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation