“Instead of the word being a thing by itself, it is represented by a 500-dimensional vector, or basically a 500 set of numbers, and each of those numbers capture some aspect of the word,” Menezes explained. To create a translation, neural networks model the meaning of each word within the context of the entire sentence in a 1,000-dimensional vector, whether the sentence is five or 20 words long, before translation begins. This 1,000-dimension model – not the words – is translated into the other language.

Source : Microsoft Translator erodes language barrier for in-person conversations – Next at Microsoft