Facebook make translation 9 times faster, more accurate

May 10, 2017, 8:06 am

   Artificial intelligence (AI) has been already in place at
FacebookTechnology company
for automatically translating status updates to other languages, but the company is making a transition from lab to app, The Verge reported on Tuesday.
   In a bid to overcome language barriers, social networking giant Facebook(facebook.com) has announced a new machine learning translation method, claiming it to be nine times faster than other competitors.
Facebook make translation 9 times faster, more accurate
   "We`re currently talking with a product team to create this work in a
FacebookTechnology company
environment.There are differences once moving from academic data to real environments in terms of language.The academic data is news-type data; while conversation on Facebook is much more colloquial," the report quoted Facebook`s AI engineer David Grangier as saying.
Alternate Title: Facebook Says It Found Faster Way to Translate Through AI

   The new machine learning translation technique has not been implemented yet and exists as a research as of now.But Facebook has told that it will likely happen further down the line.
   "Usually, AI-powered translation relies on what are called recurrent neural networks (RNNs), whereas this new research leverages convolutional neural networks (CNNs) instead," Facebook`s AI engineers explained.
     
  Facabook

   RNNs analyse date sequentially, working left to right through a sentence in order to translate it word by word while CNNs look at difference aspects of data simultaneously - a style of computation that is much improved and faster.
   "So translating with CNNs means tackling the problem more holistically and examining the higher-level structure of sentences.The [CNNs] build a logical structure, a bit like linguistics, on top of the text," said Michael Auli, another Facebook AI engineer.
     
  Have something to add to this story? Share it !

   Facebook noted that the AI community were willing to improve upon the commonly used RNNs for translation - a method that has devoured tremendous efforts already.
   "The short answer is that people just hadn`t invested as much time in this, and we came up with some new developments that made it work better," Grangier added.
   
   
 
Sponsored links