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
Pages14-22
Number of pages9
Volume191
Edition1
DOIs
StatePublished - 2009

Publication series

NameFrontiers in Artificial Intelligence and Applications
Number1
Volume191
ISSN (Print)09226389

Fingerprint

Transducers
Speech synthesis
Speech recognition
Learning algorithms
Processing

Keywords

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

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

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

Learning with weighted transducers. / Cortes, Corinna; Mohri, Mehryar.

Finite-State Methods and Natural Language Processing. Vol. 191 1. ed. 2009. p. 14-22 (Frontiers in Artificial Intelligence and Applications; Vol. 191, No. 1).

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

Cortes, C & Mohri, M 2009, Learning with weighted transducers. in Finite-State Methods and Natural Language Processing. 1 edn, vol. 191, Frontiers in Artificial Intelligence and Applications, no. 1, vol. 191, pp. 14-22. https://doi.org/10.3233/978-1-58603-975-2-14
Cortes C, Mohri M. Learning with weighted transducers. In Finite-State Methods and Natural Language Processing. 1 ed. Vol. 191. 2009. p. 14-22. (Frontiers in Artificial Intelligence and Applications; 1). https://doi.org/10.3233/978-1-58603-975-2-14
Cortes, Corinna ; Mohri, Mehryar. / Learning with weighted transducers. Finite-State Methods and Natural Language Processing. Vol. 191 1. ed. 2009. pp. 14-22 (Frontiers in Artificial Intelligence and Applications; 1).
@inproceedings{2123cc00730544afadcbc2d3d61d87f7,
title = "Learning with weighted transducers",
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.",
keywords = "Classification, Clustering, Kernels, Learning, Ranking, Rational powers series, Regression, Weighted automata, Weighted transducers",
author = "Corinna Cortes and Mehryar Mohri",
year = "2009",
doi = "10.3233/978-1-58603-975-2-14",
language = "English (US)",
isbn = "9781586039752",
volume = "191",
series = "Frontiers in Artificial Intelligence and Applications",
number = "1",
pages = "14--22",
booktitle = "Finite-State Methods and Natural Language Processing",
edition = "1",

}

TY - GEN

T1 - Learning with weighted transducers

AU - Cortes, Corinna

AU - Mohri, Mehryar

PY - 2009

Y1 - 2009

N2 - 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.

AB - 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.

KW - Classification

KW - Clustering

KW - Kernels

KW - Learning

KW - Ranking

KW - Rational powers series

KW - Regression

KW - Weighted automata

KW - Weighted transducers

UR - http://www.scopus.com/inward/record.url?scp=72749126565&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=72749126565&partnerID=8YFLogxK

U2 - 10.3233/978-1-58603-975-2-14

DO - 10.3233/978-1-58603-975-2-14

M3 - Conference contribution

AN - SCOPUS:72749126565

SN - 9781586039752

VL - 191

T3 - Frontiers in Artificial Intelligence and Applications

SP - 14

EP - 22

BT - Finite-State Methods and Natural Language Processing

ER -