• Replies 8 replies
  • Subscribers 128 subscribers
  • Views 5165 views
  • Users 0 members are here
Options
Related

Who uses Amazon's NMT or SDL's NMT? Looking for feedback.

Keenan Cooper

My coworkers and I mainly use Microsoft and Textra because of their easy integration into Trados and decent quality Japanese to English translation. The best though was Google's NMT which we used until our free trial ran out. We are currently looking to evaluate different providers for a subscription including Amazon's new NMT and SDL's NMT.

Does anyone have any experience with the quality and integration of Amazon's NMT or SDL's NMT? How do the termbase/dictionary functions work?

Thank you.
Rate translation
×
Suggest better translation
×
Moderator UI
×
  • Get AI Suggestion
Parents
  • Hi,

    About the question "How do the termbase/dictionary functions work?"

    I would say quite well
    - you can quite easily upload to cloud an existing termbase and add terms to it from the editor
    - the terms are automatically used in the translation suggestions provided

    However, I still do not understand the behaviour of the cloud termbases in terms of "fuzziness"
    Cloud termbases behave differenty from local termbases, I get too few or too many results in the term recognition window.
    It's OK if terms are used in MT suggestions only if they exactly match the source text, but too few/too many terms displayed in the term recognition window is not OK for me.

    Stefano
Reply
  • Hi,

    About the question "How do the termbase/dictionary functions work?"

    I would say quite well
    - you can quite easily upload to cloud an existing termbase and add terms to it from the editor
    - the terms are automatically used in the translation suggestions provided

    However, I still do not understand the behaviour of the cloud termbases in terms of "fuzziness"
    Cloud termbases behave differenty from local termbases, I get too few or too many results in the term recognition window.
    It's OK if terms are used in MT suggestions only if they exactly match the source text, but too few/too many terms displayed in the term recognition window is not OK for me.

    Stefano
Children
No Data