Neural Networks Applied To Machine Translation
Written by Sue Gee   
Thursday, 17 November 2016

Both Microsoft and Google have announced significant improvements to their interactive translation tool thanks to neural networks.

msmtransbanner

 

The Microsoft Translator team has announced that it is powering all its speech translation, for Skype and mobile devices, through neural networks. The blog post states:

In addition to the nine languages supported by the Microsoft Translator speech API, namely Arabic, Chinese Mandarin, English, French, German, Italian, Brazilian Portuguese, Russian and Spanish, neural networks also power Japanese text translations. These ten languages together represent more than 80% of the translations performed daily by Microsoft Translator.

To see the level of improvement you can expect, there is a Try & Compare feature on the Microsoft Translator website where you can see the outcome of the old and new methods of translation - statistical and neural. For the supplied phrases Neural does seem to perform better:

 

mstranslatenn

However, when I typed in some promotional material from a Spanish supermarket "Elegir a la carta una buena hamburguesa" I was shown an accurate translation "Choose a good hamburger á la carte" and one that missed the point entirely: "Choose a letter a good hamburger". I was initially surprised to discover that the former was the old Statistical approach but then as Statistical is influenced by the frequency of being asked to translate menus and restaurant reviews. However, the example is probably an anomaly and I'm not going to argue with Microsoft's opinion that the use of neural networks is producing superior translations. The blog post presents this graph used to promote the idea that we can expect future improvements.

 

msgraph

On the same day as  the Microsoft blog post, Barak Turovsky, Product Lead for Google Translate also made an announcement about putting Neural Machine Translation into action with an update to Google Translate: 

Introducing this roll out, Turovsky writes:

Neural Machine Translation has been generating exciting research results for a few years and in September, our researchers announced Google's version of this technique. At a high level, the Neural system translates whole sentences at a time, rather than just piece by piece. It uses this broader context to help it figure out the most relevant translation, which it then rearranges and adjusts to be more like a human speaking with proper grammar. Since it’s easier to understand each sentence, translated paragraphs and articles are a lot smoother and easier to read. And this is all possible because of end-to-end learning system built on Neural Machine Translation, which basically means that the system learns over time to create better, more natural translations.

Google Translate is using Neural Machine Translation with eight language pairs: to and from English and French, German, Spanish, Portuguese, Chinese, Japanese, Korean and Turkish. According to Google these languages are the native languages of around one-third of the world's population - however if you take into account people who speak them as second languages or have a good grasp of them the proportion of the mobile device and website users is significantly higher, likely to be the vast majority.

Machine translation does seem to be close to being the babel fish of Douglas Adam's vision. Building translation devices into a wearable with an ear piece is the next challenge.

babelfish

More Information

Microsoft Translator launching Neural Network based translations for all its speech languages

Try and Compare 

Found in translation: More accurate, fluent sentences in Google Translate

Related Articles

MIcrosoft's Project Oxford AI APIs For The REST Of Us

Google Translate - Breaking Down Babel

Skype Translator Cracks Language Barrier 

Windows Phone Translation-As-You-Go 

Word Lens - a real babel fish

Microsoft Cognitive Toolkit Version 2.0 Beta

How Will AI Transform Life By 2030? Initial Report

 

To be informed about new articles on I Programmer, sign up for our weekly newsletter,subscribe to the RSS feed and follow us on, Twitter, FacebookGoogle+ or Linkedin

 

Banner


Flox Releases Flox Hub
13/03/2024

Flox has announced that its Command Line Interface (CLI) and FloxHub are now generally available. The CLI is open source and FloxHub is free for anyone to use.



White House Urges Memory Safe Software
29/02/2024

The White House is urging developers to adopt memory safe programming languages, suggesting Rust would be a safer choice than C or C++. 


More News

 

raspberry pi books

 

Comments




or email your comment to: comments@i-programmer.info

Last Updated ( Thursday, 17 November 2016 )