Facebook’s DeepText engine is learning to read what you share like a human

Facebook has developed an engine that will enable it to better understand the context of your posts. Called DeepText, it utilizes deep neural network architecture in order to understand the text being shared. The social networking company claims that DeepText is able to understand “with near-human accuracy” the content of several thousand posts per second across 20 languages.

This technology was built on ideas developed around deep learning by Ronan Collobert and Yann LeCun from Facebook’s AI Research Group.

[aditude-amp id="flyingcarpet" targeting='{"env":"staging","page_type":"article","post_id":1966814,"post_type":"story","post_chan":"none","tags":null,"ai":false,"category":"none","all_categories":"cloud,enterprise,","session":"C"}']

Although introduced today, DeepText is already being tested across some Facebook properties, such as Messenger. The company said that the technology gives it a better understanding of people’s intentions. “DeepText is used for intent detection and entity extraction to help realize that a person is not looking for a taxi when he or she says something like, ‘I just came out of the taxi,’ as opposed to ‘I need a ride,'” the company explained in a blog post.

There’s strong motivation for Facebook to invest more in deep learning because better understanding conversational context will help the platform improve user experience as well as allowing advertisers to better target campaigns. The News Feed is just one of the areas where this kind of learning is impactful, as people want to see content that is relevant to them.

An enormous amount of data is being shared daily, not only on the social network, but across Messenger, Instagram, WhatsApp, and Oculus. Finding a way to catalog all of this information and make it easily searchable can be a daunting task, so Facebook has turned to artificial intelligence.

Though DeepText is still very much a work-in-progress, Facebook said it’ll continue to “advance DeepText technology and its applications” in collaboration with its AI research group.