ALEXANDRIA, Va., June 17 -- United States Patent no. 12,314,847, issued on May 27, was assigned to NAVER Corp. (Gyeonggi-Do, South Korea).
"Training of machine reading and comprehension systems" was invented by Julien Perez (Grenoble, France) and Quentin Grail (Meylan, France).
According to the abstract* released by the U.S. Patent & Trademark Office: "A method of using a first neural network includes: by the first neural network, receiving a text; by the first neural network, receiving a question concerning the text; and by the first neural network, determining an answer to the question using the text, where the first neural network is trained to answer the question about the text adversarially by a second neural network that is trained ...