Trados solutions include support for Language Weaver, the most powerful, comprehensive and adaptable neural machine translation platform on the market. Using machine translation enables you to translate more content and deliver it faster than before.
The translation of text by a computer, with no human involvement. Pioneered in the 1950s, machine translation can also be referred to as automated translation, automatic or instant translation.
Language Weaver, the new machine translation brand of the RWS Group, brings together the AI experts and technology from former SDL Machine Translation and Iconic Translation Machines into a single, world-class team with the most powerful, comprehensive, and adaptable neural machine translation platform on the market.
In addition, those using Trados Studio can connect to over 50 machine translation providers including DeepL, Google Translate, Microsoft MT and Modern MT by downloading an app from the RWS AppStore. Click here to find out more.
There are three types of machine translation system: rules-based, statistical and neural:
- Rules-based systems use a combination of language and grammar rules plus dictionaries for common words. Specialist dictionaries are created to focus on certain industries or disciplines. Rules-based systems typically deliver consistent translations with accurate terminology when trained with specialist dictionaries.
- Statistical systems have no knowledge of language rules. Instead they "learn" to translate by analysing large amounts of data for each language pair. They can be trained for specific industries or disciplines using additional data relevant to the sector needed. Typically statistical systems deliver more fluent-sounding but less consistent translations.
- Neural Machine Translation (NMT) is a new approach that makes machines learn to translate through one large neural network (multiple processing devices modeled on the brain). The approach has become increasingly popular amongst MT researchers and developers, as trained NMT systems have begun to show better translation performance in many language pairs compared to the phrase-based statistical approach.
When translating with Trados Studio, segments not leveraged from translation memory can automatically be machine translated for a translator to review, then accept and amend if necessary, or decide to manually translate instead. A translator can configure which machine translation to use and how much is used.
Respecting client confidentiality
If the projects you work on are commercially sensitive, your customer may require that information is not disclosed to any third parties. Carefully consider how and when to use machine translation as you could be sharing segments of the source with a third party.
Audit files are automatically generated by Trados Studio which record the use of machine translation.
Whether you are a freelance translator, LSP or corporation, working with machine translation will help increase translation productivity and allow you to take on larger volumes of work. With neural engines, machine translation output is more fluent and significantly higher quality, reducing the amount of post-editing work required.
To activate our NMT 2.0 (neural machine translation) in Trados Studio 2022, 2021 and 2019, follow these steps:
In the Translation Memory and Automated Translation dialog, add the SDL Language Cloud* translation provider to your project. To do this, select Use… and then select SDL Language Cloud from the drop-down list. In the SDL Language Cloud dialog, select SDL Machine Translation. Select a Generic – NMT translation model for the language pairs you would like to use.
For Studio 2017 users to access SDL Machine Translation's NMT 2.0, you will firstly need to download the machine translation app from the RWS AppStore.
*Please note that SDL Machine Translation is now called Language Weaver. Over the next few weeks, you will still see the old branding in some of the product pages. The wording will be updated in due course and will not impact the service you are receiving from us.
Trados Studio users can access neural machine translation from Language Weaver for free with a yearly allowance of 6 million characters per account.
If you require a larger package with a higher volume of characters per month, it is possible to upgrade to a paid plan. To hear about our flexible machine translation packages, get in touch with your local sales representative.