Smartling Announces Patent-Pending Technology That Enables Breakthrough Improvements in Translation Using AI

Smartling,the enterprise translation company,announced the introduction of patent-pending technology that brings human-quality machine translation closer to reality. With the help of Smartling’s AI technology, enterprises can now achieve breakthrough improvements in translation quality. This includes implementing style guidelines, brand voice, locale-specific conventions, grammatically accurate terminology handling and the proper use of linguistic gender preferences in translations.

Latest Insights: Embrace AI to become a W.I.T.C.H. Leader

The main challenge in implementing state-of-the-art generative AI in localization is having a scalable, end-to-end platform to make use of large language models (LLMs) that render the desired output with the necessary linguistic, factual and cultural level of precision. Smartling’s patent-pending technology addresses this challenge by designing a repeatable and predictable prompt engineering process to obtain the most suitable prompt templates for each specific use case. Smartling employs patent-pending, generative AI-powered technology that enables the use of LLMs, such as GPT-4 and ChatGPT, to ensure machine translation follows a company’s style guidelines, maintains brand voice and further perfects the grammar of the automated translation output. Additionally, this technology uses LLMs for machine translation to greatly improve a customer’s preferred terminology handling and eliminate gender bias in translations.

“Smartling’s pioneering use of generative AI and LLM technology is reshaping the way our customers translate and localize.” said Bryan Murphy, CEO of Smartling. “As a result of this new, patent-pending technology, Smartling can provide significantly more accurate and fluent translations for companies in their own brand voice, in their own style and at a fraction of the cost. In fact, our customers have been increasing their volume of machine translated content by over 225% per year while reducing their cost of translation by 60%.”

Recommended: Enhancing AI: Why New Technology Must Include Diversity

For example, today, when translating from English to Spanish, even the most advanced machine translation approaches almost always follow “masculine” word agreement and translate the word “Senator” as “Senador” or “Doctor” as “Doctor.” This is because of how gender is reflected in model training datasets. Smartling’s new, revolutionary approach produces gender-accurate translations addressing scenarios where a doctor or a senator is a female. The technology not only translates to “Senadora” and “Doctora” based on the context, but also ensures that the entire translated sentence is grammatically fluent and factually accurate.

Latest Insights: Synthetic Data: A Game-Changer for Marketers or Just Another Fad?

[To share your insights with us, please write to sghosh@martechseries.com]