top

Zero-Shot Translation - Secret Internal Language for Google’s AI Translation Tools

Back in September, Google released its Neural Machine Translation system. The search giant uses deep learning to produce better and more natural translations between languages. Google Translate in last 10 years has grown from supporting just a few languages to 103. Google Neural Machine Translation (GNMT) team is looking forward to adding a new feature to the translation system named as “Zero-shot translation”. Instructing the machine to translate English to Korean and vice versa, and also to translate English to Japanese and vice versa, the challenge arises when it is given the translation of Korean to  Japanese without taking help of English translation in between. To make it simple to understand, Google has made a gif to show the idea of Zero-shot translation. Also Read : Neural Machine Translation - Google Translate now more accurate and sophisticated The gif shows how the translation system works when this multilingual system is given the translation of English to Japanese and vice versa, also the translation of English to Korean to vice versa. Google’s multilingual system works as a single GNMT system, sharing its parameters in order to translate these four different language pairs. Sharing the parameters enables the translation system to transfer the “translation knowledge” from one language pair to the others. The visualization shows how the translation system works while translating a single sentence in different directions. Using a 3D representation of internal network data, the system translates a set of sentences including all possible pairs of the Japanese, Korean, and English languages. This “interlingua” shows a great similarity between a sentence or word in all the three languages. The interlingua is constructed with the complex neural network, therefore it is difficult to describe. Part (a) shows an overall geometry of these translations. The colors shown in the view means that the translation of a sentence from English to Korean is same as the sentence translation from Japanese to English. Part (b) zooms into one of the groups. Part (c) shows a sentence with the same meaning but from three different languages.
Rated 4.0/5 based on 20 customer reviews
Normal Mode Dark Mode

Zero-Shot Translation - Secret Internal Language for Google’s AI Translation Tools

Geneva Clark
What's New
23rd Nov, 2016
Zero-Shot Translation - Secret Internal Language for Google’s AI Translation Tools

Back in September, Google released its Neural Machine Translation system. The search giant uses deep learning to produce better and more natural translations between languages. Google Translate in last 10 years has grown from supporting just a few languages to 103.

Google Neural Machine Translation (GNMT) team is looking forward to adding a new feature to the translation system named as “Zero-shot translation”. Instructing the machine to translate English to Korean and vice versa, and also to translate English to Japanese and vice versa, the challenge arises when it is given the translation of Korean to  Japanese without taking help of English translation in between. To make it simple to understand, Google has made a gif to show the idea of Zero-shot translation.

Also Read : Neural Machine Translation - Google Translate now more accurate and sophisticated

Neural Machine Translation - Google Translate now more accurate and sophisticated

The gif shows how the translation system works when this multilingual system is given the translation of English to Japanese and vice versa, also the translation of English to Korean to vice versa. Google’s multilingual system works as a single GNMT system, sharing its parameters in order to translate these four different language pairs. Sharing the parameters enables the translation system to transfer the “translation knowledge” from one language pair to the others.

translation knowledge

The visualization shows how the translation system works while translating a single sentence in different directions. Using a 3D representation of internal network data, the system translates a set of sentences including all possible pairs of the Japanese, Korean, and English languages.

This “interlingua” shows a great similarity between a sentence or word in all the three languages. The interlingua is constructed with the complex neural network, therefore it is difficult to describe.

Part (a) shows an overall geometry of these translations. The colors shown in the view means that the translation of a sentence from English to Korean is same as the sentence translation from Japanese to English. Part (b) zooms into one of the groups. Part (c) shows a sentence with the same meaning but from three different languages.

Geneva

Geneva Clark

Blog Author
Geneva specializes in back-end web development and has always been fascinated by the dynamic part of the web. Talk to her about modern web applications and she and loves to nerd out on all things Ruby on Rails.

Leave a Reply

Your email address will not be published. Required fields are marked *

SUBSCRIBE OUR BLOG

Follow Us On

Share on

other Blogs

20% Discount