In September, Google announced that its Neural Machine Translation system will be live now. It uses deep learning to produce better, more natural translations between languages.Google AI technology has advanced a lot after the inclusion of deep learning.
Following on this success, Google Neural Machine Translation’s creators were curious about something. You can understand its power in a way that if you teach the translation system to translate English to Chinese and vice versa, and also English to Urdu and vice versa… could it translate Urdu to Chinese, 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”.
The new system, a deep learning model known as neural machine translation, effectively trains itself—and reduces translation errors by up to 87%.
Now If the computer is able to make connections between concepts and words that have not been formally linked or taught to him… does’nt that relates that the computer has formed a concept of shared meaning for those words, meaning at a deeper level than simply that one word or phrase is the equivalent of another?.
“In other words, has the computer developed its own internal language to represent the concepts it uses to translate between other languages?”. Can you imagine the extent of it .
It could be something sophisticated mechanism, or it could be something simple. But the fact that it exists at all , an original creation of the system’s own to aid in its understanding of concepts it has not been trained to understand ,that is, metaphorically speaking, pretty powerful stuff.
Neural networks have been used for machine translation since at least 2010, and other features of the system have been employed in other models in the last several years. But this is the first time that any one group has deployed all of these advances together.
The research paper describing the researchers’ work that primarily focuses on efficient multi-language translation but touching on the mysterious interlingua can be read at Arxiv.