Machine Translation

MTU Weights

Content is machine translated from English by Phrase Language AI.

MTUs Calculation

Phrase calculates MTU usage based on each character sent to a machine translation service using the following calculation:

A * (B + C) = Machine Translation Units

Where:

  • A is the total number of characters that the Customer sends for machine translation

  • B is the weight assigned by Phrase to the applicable machine translation service

  • C is the weight assigned by Phrase to reflect the additional features made available in Phrase Language AI (e.g., autoselect, QPS etc.).

Features that consume MTUs are:

  • Pre-translation

    During pre-translation, confirming segments with 100% TM matches and 101% TM matches always consumes MTUs. Correct computation of post-editing analysis requires MT suggestions.

    If segments are not confirmed during pre-translation, users can optimize the consumption of MTUs for segments with high TM fuzzy matches by disabling the option Use machine translation for segments with a TM match of 100% or more in the pre-translation settings.

  • Default analysis

    MTUs are consumed if the option Include machine translation matches (QPS) is enabled.

  • CAT editor

    Confirming segments during translation always consumes MTUs. Correct computation of post-editing analysis requires MT suggestions.

  • Phrase Language AI Portal

Machine Translation Service Weights

Type

Weight

Amazon Translate

0.5

DeepL

0.5

Google Translate

0.5

Microsoft Translator

0.5

Phrase NextGen MT

1.0

Phrase NextMT

0.5

Rozetta Translate

2.0

Tencent

0.5

Additional Feature Service Weights

Type

Weight

Additional features

0.5

Was this article helpful?

Sorry about that! In what way was it not helpful?

The article didn’t address my problem.
I couldn’t understand the article.
The feature doesn’t do what I need.
Other reason.

Note that feedback is provided anonymously so we aren't able to reply to questions.
If you'd like to ask a question, submit a request to our Support team.
Thank you for your feedback.