SDL (LSE: SDL), a leader in global content management, translation and digital experience, today announces the availability of SDL Enterprise Translation Server (ETS) 8.0, the most secure, scalable and adaptable Neural Machine Translation (NMT) solution on the market today, used by global enterprises worldwide. With a powerful new dictionary feature enabling businesses to add specific terminology controls, the ability to automatically translate text on images, as well as greater user control for adapting translations, SDL ETS 8.0 provides businesses with the highest-quality translation output.
SDL ETS 8.0 is designed specifically for any global enterprise looking to transform the way they understand, communicate, and deliver multilingual content, enabling them to securely translate large volumes of content into one or more languages quickly. Offering total control and security of translation data, SDL ETS has been successfully used in the government sector for over 15 years.
“Companies today are overwhelmed with the sheer volume of multilingual content they have to contend with to understand customers, as well as effectively communicate and collaborate across the globe,” said Mihai Vlad, VP of Machine Learning, SDL. “By quickly translating any type of content, SDL ETS helps enterprises to facilitate internal content analysis and consumption to rapidly uncover what is relevant and address global business issues and needs, all with agility and speed.
“Another key requirement for successful MT use is the ability to get the system to learn and adapt to enterprise-specific linguistic requirements and preferences. This has been especially challenging with NMT technology which, until now, has been difficult to do without undermining the output quality. The ease, flexibility and tailoring capability of SDL ETS 8.0, means enterprises can easily adapt NMT across multiple departments that have differing terminology, yet still maintain the translation fluency that this latest generation of MT technology is acclaimed for,” continued Vlad.
SDL’s latest dictionary feature also sets a new industry standard for user control over automated translations, allowing users across the enterprise to use different dictionaries without impacting the quality of the translations, which has been especially hard to do with NMT until now. SDL ETS 8.0 Dictionary capabilities include:
- Controls that allow an enterprise to enforce multiple terminology and translation preferences for the same word, something that is necessary for different departments who may have unique interpretations for the same word or term.
- Easy implementation of preferred terminology and personalization by any user with no upfront technical knowledge or training required – another industry first for MT.
- Deployment of multiple dictionaries in a single engine at the same time, allowing multiple departments with differing needs to optimize the MT engine differently.
- Terminology preferences that can be changed and modified on an ongoing basis to accommodate changing business and communication priorities.
Furthermore, with SDL ETS 8.0, enterprises can benefit from greater security and access APIs for developers, while enhancing connectivity between systems and processes to help regulated industries comply with stringent legislative requirements. Other new SDL ETS 8.0 benefits include:
- Easy Image Translation: Translating visual content has traditionally been a cumbersome task, usually involving the manual extraction of text from image sources, translation of the text itself, and then laying out the text back into the image. SDL has added translation support for various image file formats (.jpg, .jpeg, .gif, .png, .tiff, .tif), enabling images to become a seamless part of the translation supply chain and bypassing text extraction and submission procedures.
- Vary and Combine Languages: Brands can also now add multiple language pair variants to the same translation engine. As an example, a generic Arabic to English language pair and an informal Arabic to English pair can both be active at the same time and concurrently process incoming translations. This helps enterprises develop a richer set of language and vocabulary to engage with varying local customer needs across any language.