According to news, the Google Brain’s artificial intelligence (AI) can create its own universal language or the so-called interlingua. It is not actually something that you can learn or teach so much, but an algorithm by which the AI can learn how to translate between languages, without actually knowing either. Google Neural Machine Translation (GNMT) system is a machine learning based system capable of performing language translations effectively. And indeed, Google really make it happen to translate a language to any other languages.
Google Brain Has Its Own Translator That Can Detect Any Language
Just last September, Google announced that its Neural Machine Translation system had gone live. It uses deep learning to a quality and more natural translations between languages. But GNMT’s creators were curious about something more.
To fully understand this new system of development, TechCrunch gave an example: If you teach the translation system to translate English to Korean and vice versa, and also English to Japanese and vice versa… could it translate Korean to Japanese, without resorting to English as a bridge between them? They made this helpful gif to illustrate the idea of what they call “zero-shot translation.”
"An example of this would be translations between Korean and Japanese where Korean⇄Japanese examples were not shown to the system," the Mike Schuster, from Google Brain wrote in a blog post.
The Interlingua
An interlingua is a type of artificial language, which is used to fulfill a purpose. In this case, the interlingua was used within the AI to explain how unseen material could be translated
According to The Inquirer, uses lessons learned from what it does know to find the commonalities that will allow it to deduce what it doesn’t. It encoded the semantics rather than trying to translate the phrase verbatim.
"The described Multilingual Google Neural Machine Translation system is running in production today for all Google Translate users. Multilingual systems are currently used to serve 10 of the recently launched 16 language pairs, resulting in improved quality and a simplified production architecture."
