In an official blog post, the social network giant, Facebook announced a new software based on Machine Learning technology and is capable of translating 100 languages without relying on English. The new AI-based Machine Learning software is important to Facebook as they claim to power over an average of 20 billion translations every day on Facebook News Feed, and they hope the new system will deliver better results to users.
According to Facebook, nearly two-thirds of all users use other languages apart from English and the new open-source artificial intelligence software is created to help the massive social network deliver content better in 160 languages to its more than two billion users around the world.
“When translating, say, Chinese to French, most English-centric multilingual models train on Chinese to English and English to French, because English training data is the most widely available. Our model directly trains on Chinese to French data to better preserve meaning. It outperforms English-centric systems by 10 points on the widely used BLEU metric for evaluating machine translations. M2M-100 is trained on a total of 2,200 language directions — or 10x more than previous best, English-centric multilingual models. Deploying M2M-100 will improve the quality of translations for billions of people, especially those that speak low-resource languages.” Angela Fan wrote in a blog post, Facebook Research Assistant.
“Breaking language barriers through Machine Learning translation is one of the most important ways to bring people together, provide authoritative information on COVID-19, and keep them safe from harmful content,” Angela Fan continued.
The company also said that it is releasing the data set, model, training and evaluation setup as open-source to the research community to build more support on top. It’s open-sourced here.