Learning efficiency of very simple grammars from positive data

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

The class of very simple grammars is known to be polynomial-time identifiable in the limit from positive data. This paper gives an even more general discussion on the efficiency of identification of very simple grammars from positive data, which includes both positive and negative results. In particular, we present an alternative efficient inconsistent learning algorithm for very simple grammars.

Original languageEnglish
Pages (from-to)1807-1825
Number of pages19
JournalTheoretical Computer Science
Volume410
Issue number19
DOIs
Publication statusPublished - 2009 Apr 28
Externally publishedYes

Keywords

  • Grammatical inference
  • Identification in the limit
  • Learning efficiency
  • Very simple grammars

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)

Fingerprint Dive into the research topics of 'Learning efficiency of very simple grammars from positive data'. Together they form a unique fingerprint.

  • Cite this