Microsoft Translator, Azure AI receive upgrades in efficiency and quality

Microsoft’s utilizing a new family of AI models dubbed Z-code, which provides the quality and performance of large-scale language models with the added benefit of greater efficiency.

“With Z-code we are really making amazing progress because we are leveraging both transfer learning and multitask learning from monolingual and multilingual data to create a state-of-the-art language model that we believe has the best combination of quality, performance and efficiency that we can provide to our customers,” said Xuedong Huang, Microsoft technical fellow and Azure AI chief technology officer.

Part of what makes Z-code special is its ability to derive solutions from model portions rather than the entire thing, which makes Z-code usage scalable and efficient. It’s being utilized within Azure AI via the Microsoft Translator app, wherein it’s helping expand the capabilities of Translator for less common languages and helping improve results of even the most common translation requests for popular languages such as English and French.

Z-code model translates English to French.Source: Microsoft

For specific numbers on how the model family is helping Microsoft, here are hard figures the company provided regarding Z-code’s effects on translation: “The models improved English to French translations by 3.2 %, English to Turkish by 5.8 %, Japanese to English by 7.6%, English to Arabic by 9.3% and English to Slovenian by 15%.”

In other words, should you want to translate anything to or from English, the odds are Z-code is going to help that process. For more technical details on AI models, check out Microsoft’s blog posts on the subject. And if you want to know more about the NVIDIA GPUs helping power these innovations, there’s news on that too.