09:17 08 June 2016
Facebook, which currently has over a billion users all around the globe, has developed a new artificial intelligence to automate the process of sifting through enormous information being posted by members on a daily basis.
The technology, called DeepText, can understand text in various different languages. It was developed to help catch unwanted content and to generate the right results from search queries and requests.
In a blog post, Facebook said: "DeepText leverages several deep neural network architectures, including convolutional and recurrent neural nets, and can perform word-level and character-level based learning,"
The software is currently being tested with Facebook Messenger and will soon move out across the entire network.
"Text understanding includes multiple tasks, such as general classification to determine what a post is about — basketball, for example — and recognition of entities, like the names of players, stats from a game, and other meaningful information," the company said.
"But to get closer to how humans understand text, we need to teach the computer to understand things like slang and word-sense disambiguation. As an example, if someone says, “I like blackberry,” does that mean the fruit or the device?"