Learning with weighted transducers

Corinna Cortes, Mehryar Mohri

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Weighted finite-state transducers have been used successfully in a variety of natural language processing applications, including speech recognition, speech synthesis, and machine translation. This paper shows how weighted transducers can be combined with existing learning algorithms to form powerful techniques for sequence learning problems.

Original languageEnglish (US)
Title of host publicationFinite-State Methods and Natural Language Processing
PublisherIOS Press
Pages14-22
Number of pages9
Edition1
ISBN (Print)9781586039752
DOIs
StatePublished - 2009

Publication series

NameFrontiers in Artificial Intelligence and Applications
Number1
Volume191
ISSN (Print)0922-6389

Keywords

  • Classification
  • Clustering
  • Kernels
  • Learning
  • Ranking
  • Rational powers series
  • Regression
  • Weighted automata
  • Weighted transducers

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Learning with weighted transducers'. Together they form a unique fingerprint.

  • Cite this

    Cortes, C., & Mohri, M. (2009). Learning with weighted transducers. In Finite-State Methods and Natural Language Processing (1 ed., pp. 14-22). (Frontiers in Artificial Intelligence and Applications; Vol. 191, No. 1). IOS Press. https://doi.org/10.3233/978-1-58603-975-2-14