Facebook's new system helps it detect offensive memes

Facebook's 'Rosetta' AI can extract text from a billion images daily

Facebook's 'Rosetta' AI can extract text from a billion images daily

At its core, Rosetta was developed as a way of enabling photo search, or for making Facebook more accessible for users who are visually impaired. Memes have become a great source to entertain people, convey a message or any other objective on the social media platform. As a large number of posts are being posted on the social media, Facebook's moderators aren't able to review the content of the memes while they are being posted, creating a lot of fuss related to offensive posts.

Every day, Rosetta extracts text in a variety of languages from more than a billion publicly shared images on Facebook and Instagram.

"Text extracted from images is being used to improve the relevance and quality of photo search, automatically identifying content that violates our hate-speech policy on the platform in various languages, and improve the accuracy of classification of photos in News Feed to surface more personalised content", the networking giant noted. The company plans to keep on growing the number of languages it can understand and to make it better at extracting text from video frames. It then interprets the text based on transcription. Such tools are being used on various platforms and, the technology isn't new.

The technology is rooted in optical character recognition (OCR), only here it's been objective built to process images that get uploaded to Facebook on a daily basis.

SC coastline battered as Hurricane Florence lands
While Florence has lost some of its strength, it is still considered an extremely risky and life-threatening storm. In the meantime, "treat the inland flooding just as seriously as you would the storm surge", said Clark.

In the first quarter of the year, Facebook said it removed roughly 2.5 million pieces of hate speech - only 38% of which was flagged by automated systems. The AI tool will be effective enough to understand multiple languages. New tools are now being worked on that the company hopes will do an even better job at that task. There are simply too many users and too many posts to lay content moderation exclusively on the shoulders of human workers.

Facebook is doing a lot of improvements in its artificial intelligence sector.

Its solution is Rosetta, which was built with the same system as the OCR but is far more powerful. It is indeed a great way to block hatred speech and offensive posts on the platform.

Recommended News

We are pleased to provide this opportunity to share information, experiences and observations about what's in the news.
Some of the comments may be reprinted elsewhere in the site or in the newspaper.
Thank you for taking the time to offer your thoughts.