ALEXANDRIA, Va., July 7 -- United States Patent no. 12,675,635, issued on July 7, was assigned to AMAZON TECHNOLOGIES INC. (Seattle).
"Training natural language processing network based on existing network" was invented by Steven L. Teig (Menlo Park, Calif.), Eric A. Sather (Palo Alto, Calif.) and Evgeny Sorkin (Vancouver, Canada).
According to the abstract* released by the U.S. Patent & Trademark Office: "Some embodiments provide a method for training a first NLP network based on a previously-trained second NLP network. The method propagates text inputs through the first network to generate a first set of output vectors and the second network to generate a second set of output vectors. Each first-set vector generated based on a text inpu...