Facebook researchers propose using language models for fact-checking

http://feedproxy.google.com/~r/venturebeat/SZYF/~3/PEH-X0nrGz0/

In a paper published on the preprint server Arxiv.org, researchers at Facebook propose using natural language models as fact-checkers, inspired by the fact that models trained on documents from the web display a surprising amount of world knowledge. Their proposed approach employs a verification classifier model that when given an original claim and a generated claim determines whether the claim is supported,  » ….