Is machine translation ready yet?

  • Garcia I
  • 48

    Readers

    Mendeley users who have this article in their library.
  • 21

    Citations

    Citations of this article.

Abstract

The default option of the Google Translator Toolkit (GTT), released in June 2009, is to “pre-fill with machine translation” all segments for which a ‘no match’ has been returned by the memories, while the Settings window clearly advises that “[m]ost users should not modify this”. To confirm whether this approach indeed benefits translators and translation quality, we designed and performed tests whereby trainee translators used the GTT to translate passages from English into Chinese either entirely from the source text, or after seeding of empty segments by the Google Translate engine as recommended. The translations were timed, and their quality assessed by independent experienced markers following Australian NAATI test criteria. Our results show that, while time differences were not significant, the machine translation seeded passages were more favourably assessed by the markers in thirty three of fifty six cases. This indicates that, at least for certain tasks and language combinations — and against the received wisdom of translation professionals and translator trainers — translating by proofreading machine translation may be advantageous.

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

Authors

  • Ignacio Garcia

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free