Microsoft improves its AI translations with Z-Code – TechCrunch

Microsoft today announced an update to its translation services that, thanks to new machine learning techniques, promises significantly improved translations between a large number of language pairs. Based on its Project Z-Code, which uses a "spare Mixture of Experts" approach, these new models now often score between 3% and 15% better than the company's previous models during blind evaluations. Z-Code is part of Microsoft's wider XYZ-Code initiative that looks at combining models for text, vision and audio across multiple languages to create more powerful and helpful AI systems. At its core, the system basically breaks down tasks into multiple subtasks and then delegates them to smaller, more specialized models called "experts." The model then decides which task to delegate to which expert, based on its own predictions.