Facebook developing an AI engine to read between lines for text posted by users

Facebook announced that it is developing an AI engine, called Deep Text, which will understand thoughts and sentiments behind a text posted by a user on his Facebook account to help users in many ways by supplying useful information and also to keep check on spam.

The development of this new system may transform this social networking website into a powerful search engine. The social networking website is used by billion of people every day. They keep updating their status, post events, photos and video that is seen by other users across globe with similar interest.

There is more potential in Facebook than what it can presently do. The company can use this platform to benefit people in other deferent ways. In addition to connecting people with those having similar interests, to sell more ads, it can also help people find things they are searching for.

“We want Deep Text to be used in categorizing content within Facebook to facilitate searching for it and also surfacing the right content to users”, said Hussein Mehanna, an engineering director at Facebook’s machine learning team.

Facebook already uses demographic information shared by users. Currently, no text based information posted by its users is used by Facebook. This is where; Deep Text will play its role in understanding motive behind putting a text online.

The system is currently under-development. Once completed, Deep Text will assist in categorizing and providing meaning to all information in the text. The engine will alter unstructured data into useful information. By understanding the text, the social media platform can help users share that with people who matter.

“These are the big applications for Facebook’s newest artificial intelligence system called “DeepText”. 400,000 new stories and 125,000 comments on public posts are shared every minute on Facebook. DeepText will help Facebook analyze several thousand per second across 20 languages with near-human accuracy,” according to a news report published by Tech Crunch.

But at the same time DeepText could help Facebook weed out harassment and abuse. If it can automatically pick out hate speech from status updates that merely contain controversial terms, it could prevent a human from ever suffering the harassment and having to report it manually. Facebook already says that its AI systems report more offensive photos than humans on its social network.

With DeepText and its other image recognition AIs, Facebook could make huge improvements in how it routes content from authors to viewers. That could give it a leg-up over other social networks like Snapchat or Twitter without the know-how or product design to aggressively filter and suggest what people see.

The gap between the AI haves and have-nots is widening. If every News Feed post looks interesting, you’ll spend more time on Facebook, you’ll share more text there, DeepText will get smarter, and the Facebook AI feedback wheel will spin faster and faster towards becoming the perfect content recommendation engine.

According to a story published on the topic by Mashable, “Introduced Wednesday, DeepText offers an intriguing look into how Facebook is using artificial intelligence to make its platform better at parsing the billions of lines of text that pass through it each day.”

This may sound a bit dystopian but the goal of DeepText is to more precisely understand the content and context of text on Facebook, in order to improve its overall user experience. And Facebook is already experimenting with this technology in a couple different ways.

On Messenger, for example, it’s being used for something Facebook calls “intent extraction” — figuring out the difference between messages that may sound similar but have very different meanings. Writing “I need a ride,” for instance, may trigger a prompt for you to call an Uber but writing “I found a ride,” shouldn’t.

Some of these improvements may sound like minor changes, projects like DeepText are going to be increasingly important to the company as it pushes further into AI. That’s because the better Facebook is at understanding what you’re talking about, the better it will be at curating your News Feed, or keeping your conversations within Messenger and hiding spam — all of which stand to keep more people on Facebook and Facebook products for longer.

A report published in Venture Beat informed, “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.”

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.

Leave a Reply

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