Machine Translation

Phrase Translate (TMS)

Phrase Translate is the machine translation (MT) hub and an add-on with additional features. Its AI-powered MT autoselect feature finds the optimal engine for each translation job based on its domain and language pair. Translating can start with Phrase Translate's fully managed engines or supported engines can be added via API. MT quality estimation supporting many language pairs is enabled for all engines by default. Glossaries can also be associated with MT engines that support them.

  • Multiple instances of Phrase Translate can not be created.

  • Fully managed engines are presented on the Phrase Translate Dashboard tab or if MT profiles are enabled, on the Phrase Translate profile page. Fully managed engines can be switched on and off from these locations.

  • The Charts tab presents charts and graphs of how Phrase Translate is being used and full results can be downloaded from the download.jpg icon on the top right of each graph.

  • Total character consumption is defined as the total number of characters that were requested for MT translation. This includes all translated characters, all translations that resulted in error, and characters translated from cache. Previous versions of the chart included only translated characters, so slightly larger character counts may be reported in the charts.

  • Phrase Translate for post-editing is not designed for workflows that by-pass the post-editing step (raw MT).

MT Autoselect Supported Languages

MT Autoselect supports domain-based recommendation for all documents in these source languages:

  • English

  • Czech

  • German

  • Spanish

  • French

  • Italian

  • Japanese

  • Korean

  • Dutch

  • Russian

  • Swedish

  • Chinese Simplified

All other language combinations get MT Autoselect recommendations but do not take text domain into account.

Domains

The type of content translated with machine translation can significantly affect the quality of the output. An engine that might perform well for product descriptions might struggle with a medical report. The content type variable is known as a domain.

Categorizing documents into domains is normally a process that requires human input, creating complications when it comes to scaling translation and allows for basic human error.

Domains were created automatically using an AI-powered analysis of documents. An unsupervised machine learning algorithm recognized 11 distinct types of documents that shared similar sets of keywords:

Domain

Keywords

Medical

‘study’, ‘patients’, ‘patient’, ‘treatment’, ‘dose’, ‘mg’, ‘clinical’

Travel and Hospitality

‘km’, ‘hotel’, ‘guests’, ‘room’, ‘accommodation’

Business and Education

‘team’, ‘business’, ‘work’, ‘school’, ‘students’

Legal and Finance

‘agreement’, ‘company’, ‘contract’, ‘services’, ‘financial’

Software User Documentation

‘click’, ‘select’, ‘data’, ‘text’, ‘view’, ‘file’

Consumer Electronics

‘power’, ‘battery’, ‘switch’, ‘sensor’, ‘usb’

User Support

‘please’, ‘email’, ‘account’, ‘domain’, ‘contact’

Cloud Services

‘network’, ‘server’, ‘database’, ‘sql’, ‘data’

Industrial

‘mm’, ‘pressure’, ‘valve’, ‘machine’, ‘oil’

Software Development

‘value’, ‘class’, ‘type’, ‘element’, ‘string’

Entertainment

‘game’, ‘like’, ‘get’, ‘love’, ‘play’, ‘go’

Configure Phrase Translate

Fully managed machine translation engines can be activated and deactivated from the Phrase Translate page (access from the left-hand navigation panel).

Additional engines can be added if the API key for the engine is available.

To add an additional engine, follow these steps:

  1. From the Phrase Translate page, click an additional machine translation engine.

    The page for the selected engine opens.

  2. Provide the API Key.

  3. If required, provide additional information for the engine.

  4. Click Save.

    The configured engine is available for activation.

Post-editing with Phrase Translate

The Phrase Translate add-on for post-editing offers unlimited MT for post-editing purposes.

Important

Post-editing with Phrase Translate is defined as a process wherein a linguist edits and corrects all machine translated output generated by one of Phrase Translate’s fully managed engines in the editor.

All required content can be machine translated as long as it is post-edited by linguists with there being a human limitation to the amount of content that one linguist can process.

To ensure that more content than can be post-edited with Phrase Translate is not being processed in machine translation:

  • Perform all post-editing in the editor.

  • Disable MT pre-translate for content intended for human translation or raw MT.

  • Running an analysis with included machine translation matches should only be done for content intended for post-editing.

  • Purchase more user seats or upgrade to a higher edition.

MT Profiles

MT profiles can be created with different settings and be applied to different projects. Created profiles are available for selection in project settings.

To create a machine translation profile, follow these steps:

  1. From the Machine translation engines panel on the Phrase Translate page, click Enable multiple profiles.

    The Machine translation profiles table is presented.

  2. Click Add MT profile.

    The New Phrase Translate profile window opens.

  3. Provide a name for the profile and click Create.

    The configuration page for the profile is presented.

  4. Configure profile as required and click Back to list.

    The new profile is presented in the Machine translation profiles table.

Profiles can be edited, assigned as default, deleted or duplicated from the edit.svgmenu to the right of the profile name.

Tip

  • If purchasing characters directly through Google or Microsoft, set these engines up on the machine translation page.

  • Free characters provided by Microsoft Translator can still be used by disabling Phrase Translate and setting up the Microsoft Translator account.

Supported Fully Managed Machine Translation Engines

  • Alexa Translations A.I. (formerly Yappn)

  • Amazon Translate

  • Autodesk NMT

  • DeepL

  • Google AutoML

    Note

    When adding Google AutoML to Phrase Translate, Bucket name is required information due to support and potential usage of MT glossaries.

  • Google Translate

    Important

    As of November 3rd, 2020, all new projects created with Google Translate as the selected engine will automatically use Google’s Neural Machine Translation (NMT) engine by default instead of Google’s Statistical Machine Translation (SMT) engine.

  • Human Science

  • Lengoo HALOS

  • Microsoft Custom Translator (in Microsoft Azure, set location to "global")

  • Microsoft Translator / Microsoft Translator Hub

  • NpatMT

  • Phrase NextMT

  • Rozetta T-4OO Realtime

  • Systran PNMT

  • Tencent TranSmart

    Important

    Only available through Phrase Translate. Supports zh -> en and en-> zh translations (simplified Chinese only).

  • Ubiqus NMT

  • Yandex

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.