TECHBYTE: Google's Neural Machine Translation System went live in September. Its a machine language based system for performing language translations effectively. Google's AI and language developer thinks that it is using its own internal language to translate it.
Since September Google announced that its Natural Machine Translation System had gone in live. Google Neural Machine Translation (GNMT) system is a machine learning based system capable of performing language translations effectively . Google has done a lot of research to enhance its translation capabilities . Now its tries to understand a complete meaning of sentence instead of individual words and phrases to translate .
GNMT’s creators were curious about something. 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 have developed a concept they call “Zero-Shot Translation”. Google’s Multilingual Neural Machine Translation system is able to translate a pair of languages It involves a single Neural Translation Machine (NMT) model to translate between multiple language pairs.
The researchers trained the system with examples of Japanese⇄English and Korean⇄English pairs.The system was expected to perform Korean⇄Japanese translations, although, it was never taught to do so. It
performed the Korean⇄Japanese translation up to a reasonable extent.
It produces "reasonable" translations between two languages that it has not explicitly linked in any way, means no English allowed. This raised a quation-
According to the researchers, the system has developed its own language,
or “interlingua”, using which it relates different languages according
to their sentence semantics rather than focusing on sentences
phrase-to-phrase.
The Multilingual Google Neural Machine Translation has been implemented
for Google Translate. Also, 10 of the 16 newest language pairs are being
translated using multilingual system.
0 comments:
Post a Comment