AI of “Interlingua”
Neural networks are machines and algorithms developed to behave like the human brain—but a development from Google Translate shows that (once again) AI can outperform humans in a big way. Google’s AI can now translate language pairs it has not been trained for. To be clear, this means that it can translate between languages that it wasn’t taught to translate. This works if the AI first translates both of the languages into a common language that it knows.
The development is detailed in a paper published on Cornell University’s arXiv.
To break this down, Google recently upgraded Translate to the company’s deep-learning Google Neural Machine Translation (GNMT) system, paving the way for a slew of improved capabilities. In a blog post, researchers from the team, which is aptly called Google Brain, discussed how this new “Zero-Shot Translation” works. In short, the system is able to automatically group sentences and phrases with the same meaning. It then links together meaning through previously-learned languages in what the developers call “interlingua”.