Language selection

Government of Canada / Gouvernement du Canada

Search

Machine translation: overview

From National Research Council Canada

DOIResolve DOI: https://doi.org/10.1016/B0-08-044854-2/00936-6
AuthorSearch for: 1; Search for: 1
Affiliation
  1. National Research Council of Canada
FormatText, Book Chapter
Subjectautomatic translation; corpus-based machine translation; direct machine translation; example-based machine translation; interlingual machine translation; knowledge-based machine translation; rule-based machine translation; statistical machine translation; transfer-based machine translation; translation architectures; translation difficulties
Abstract
Machine translation – the use of computers to translate automatically among human languages – is an alluring prospect, one that for more than 50 years has fascinated researchers, inspired idealists and opportunists, and provoked unease among professional translators. This article gives a broad survey of this diverse and active field. It begins with a description of the many challenging problems faced by designers of machine translation systems and explains why there appears to be slim hope of attaining human-level performance in the foreseeable future. With these problems in mind, this article examines the main symbolic and empirical translation methods, and tries to give a balanced picture of their strengths and weaknesses.
Publication date
PublisherElsevier
In
  • Encyclopedia of Language & Linguistics: 2nd edition (2006): 404–422.
LanguageEnglish
Peer reviewedYes
NPARC number23000866
Export citationExport as RIS
Report a correctionReport a correction (opens in a new tab)
Record identifier23c2af70-7403-4eed-958e-55dcd9bf2531
Record created2016-10-26
Record modified2020-06-16
Date modified: