Back to top image

🦾 Machine Translation & MT Profiles

 

Machine Translation (MT) is a cost-effective way of translating content at a rapid speed. Traditionally, MT has been a mechanical, rule-based substitution of words in a source language to a target, but advances in deep learning and machine learning have yielded more advanced, high-quality translation performance.

Tip: Need to translate text or files instantly without any configuration? Try Smartling Translate - Smartling's new machine translation portal, powered by Smartling's NMT Hub.

MT Providers and Support Languages

Smartling integrates with the following Machine Translation engines:

* Includes support for custom trained engines.

** In addition to the supported locales mentioned here, Prompsit can also be used to translate from or into the following English locales:

  • English (Canada): This locale uses the same translation output as English (United States).
  • English (Australia), English (Singapore), English (Mauritius), English (New Zealand) and English (South Africa): These locales use the same translation output as English (Great Britain).

To connect your Smartling account to an MT engine, you will first need to activate an account with one of the above providers. Please contact your CSM for more details.

MT Profiles

MT Profiles are a collection of configurations for your MT engines used in Smartling. You can create an MT Profile to store a key, then assign that profile to different workflows. You can also use your MT credentials in the CAT Tool by designating an MT Profile. Furthermore, you can add an MT optimized glossary to any MT Profile, so that your glossary terms are used in your machine translations.

Smartling Auto Select

Smartling Auto Select is Smartling's-own MT Profile. For information on the Smartling Auto Select MT Profile, read our documentation on Smartling Auto Select.

Creating an MT Profile

For information on how to create, edit, delete and configure an MT Profile in Smartling, read our documentation on Configure MT Profiles in Machine Translation Settings.

Enabling MT Profiles in the CAT Tool

For information on how to enable MT Profiles in the CAT Tool, read our documentation on Machine Translation in the CAT Tool.

Enabling MT Profiles in Workflows

For information on how to enable MT Profiles in workflows, read our documentation on Configure MT Profiles in Workflows.

Machine Translation in the Translation Memory

For information on machine translation in the translation memory, read Machine Translation in the Translation Memory.

MT Errors

For information on MT errors, read our documentation on Troubleshooting MT Errors.

MT Profiles and Glossaries

For more information on integrating your glossary with an MT Profile, read our documentation on Insert Glossary Terms In Machine Translations.

Locale-specific Machine Translation

Machine Translation generally facilitates the translation of one language into another, without taking into consideration locale-specific nuances. For example, most MT providers will generate the same translation output for French (France) and French (Canada). Regional or country-specific variations of the same target language are generally not taken into account.

Cross-locale Adaptation with Prompsit

If you are interested in adapting text from one locale to another with MT, e.g. English (United States) to English (United Kingdom), we would recommend setting up an adaptation workflow using Prompsit.

Locale-specific MT with Smartling Auto Select

Smartling Auto Select provides a locale-specific Machine Translation output for the following target languages, taking into account regional nuances:

  • French: French (France) vs. French (Canada)
  • Portuguese: Portuguese (Portugal) vs. Portuguese (Brazil)
  • Spanish: Spanish (Spain) vs. Spanish (Latin America)
  • English: English (United States) or English (Canada) vs. English (United Kingdom) or English (Australia), English (Singapore), English (Mauritius), English (New Zealand), English (South Africa)

This is achieved by using Prompsit to automatically adapt the Machine Translation output to the specific target locale, regardless of the MT provider which was selected for the initial translation.

Table of Contents