Social media giant Facebook today announced the introduction of a new Artificial Intelligence Deep Learning Based Text Understanding Engine called ‘DeepText’. This can analyse what people are writing about in posts with near-human accuracy across 20 languages.
“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,”.
DeepText leverages several deep neural network architectures, including convolution and recurrent neural nets, and can perform word-level and character-level based learning.
On Why deep learning, Facebook explained, “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. 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?”
Facebook already says that its AI systems report more offensive photos than humans on its social network.
The company also revealed that “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?”
The deep learning-based text understanding engine is already being tested on Facebook Messenger.
Facebook aims to use that ability to make better recommendations to people, both about related posts and related services available on Facebook and to improve people’s experiences.
“DeepText” can also be used to filter out spam or any other undesirable content and present more of the content that people want to see.