Meta Created AI To Check Facts On Wikipedia
Meta has partnered with the Wikimedia Foundation to create an artificial intelligence model that automatically scans Wikipedia citations to check their accuracy, according to Engadget. She may also suggest alternative quotations if she finds a passage with an unreliable source.
Artificial intelligence from Meta uses a natural speech comprehension transformation model that tries to understand the different relationships of words and phrases in a sentence. The model is based on the Meta Sphere database, which consists of more than 134 million pages.
Sphere uses a natural language comprehension (NLU) transformation model that tries to understand the different relationships of words and phrases in a sentence.
The Sphere database consists of 134 million web pages. The natural language understanding algorithm parses the footnotes in encyclopedia articles and looks for a single source to verify each statement.
The company says Sphere can analyze “tens of thousands” of quotes at once. Meta noted that the electronic encyclopedia is replenished with 17,000 articles at a time, containing many footnotes that are difficult to check manually.
In addition, Meta plans to create a platform that Wikipedia editors can use to systematically review and correct footnotes.
