Translation Memory & Machine Translation Dj Vu combines both - PowerPoint PPT Presentation

Translation Memory & Machine Translation Déjà Vu combines both smartly!

Content • Machine Translation and Translation Memory • MT Integrations in Déjà Vu X3 • How to use them in Déjà Vu X3? • How to combine them in Déjà Vu X3? • What is coming next?

Introduction Machine Translation has become incontrovertible in the translation industry. Deja Vu’s Machine Translation module has, therefore, a complete set of options for full flexibility and customization . It can be applied at different levels, particularly to combine your databases with Machine Translation intelligently for increased productivity. This document describes how to configure and efficiently use one of the many Machine Translation providers currently integrated in Déjà Vu X3.

Select your MT provider a. Through File > Options > Machine Translation

Select your MT provider b. Within a specific project, through the Project tab in the ribbon, by clicking on Properties and selecting the Machine translation tab

Select your MT provider • Google • Systran • Microsoft Translator / Microsoft Translator Hub • PROMT • Itranslate4.eu • MyMemory • Asia Online

Select your MT provider • Google

Select your MT provider • Systran • Server-based

Select your MT provider • Microsoft Translator • Microsoft Translator Hub

Select your MT provider • PROMT • Server-based

Select your MT provider • itranslate4.eu

Select your MT provider • Asia Online • Server-based In order to use Asia Online, specify your URL, Port, Account No, Username, Password, and the required attributes.

Select your MT provider Combine multiple MT providers in one project and according to specific language pairs • You can add as many MT providers as you like to one project • Assign specific MT providers to particular language pairs within a multilingual project

Machine Translation Calls Machine Translation results can be configured at several levels and for different actions: Menu Translation (File > Options) / Pretranslate (Project tab)

Machine Translation Calls 1. In the Pretranslation: The whole segment is translated with MT if no match, neither exact nor fuzzy, is available in the Translation Memory.

Machine Translation Calls 2. For Fuzzy match repair: Repairs fuzzy matches with MT unless DeepMiner statistical extraction is activated, resulting in retrieved data from your translation memory. Deja Vu will always prioritize your database entries over MT

Machine Translation Calls 3. To Assemble: Deja Vu attempts to construct a translation by piecing together translations for all terms and phrases in the source segment

Combine MT&TM – A match repaired with Machine Translation will usually be better than a normal fuzzy match, and better than an entire Machine Translated segment. – Your own data is considered to be of higher quality and will always have priority over the Machine Translation results.

Conclusion • Translation Memory System and Machine Translation System : – antagonist ? – complementarity? This module is just the beginning of the story and we will continue working in this direction, with integration of additional Machine Translation providers and more advanced options to come in the near future. • So, go ahead with our new module, and experience it yourself!

Contact us www.atril.com contact@atril.com +33 149 709 560