An algorithm for the unsupervised learning of morphology

  • Authors:
  • John Goldsmith

  • Affiliations:
  • Departments of Linguistics and Computer Science, 1010 East 59th St., The University of Chicago, Chicago, IL 60637, USA e-mail: goldsmith@uchicago.edu

  • Venue:
  • Natural Language Engineering
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper describes in detail an algorithm for the unsupervised learning of natural language morphology, with emphasis on challenges that are encountered in languages typologically similar to European languages. It utilizes the Minimum Description Length analysis described in Goldsmith (2001), and has been implemented in software that is available for downloading and testing.