US Patent Issued to GOOGLE on Jan. 13 for "System(s) and method(s) to reduce a transferable size of language model(s) to enable decentralized learning thereof" (American, Swiss Inventors)

ALEXANDRIA, Va., Jan. 13 -- United States Patent no. 12,524,679, issued on Jan. 13, was assigned to GOOGLE LLC (Mountain View, Calif.).

"System(s) and method(s) to reduce a transferable size of language model(s) to enable decentralized learning thereof" was invented by Mingqing Chen (Saratoga, Calif.), Lara McConnaughey (San Francisco), Kaan Ege Ozgun (Zurich), Rajiv Mathews (Sunnyvale, Calif.) and Francoise Beaufays (Mountain View, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Implementations disclosed herein are directed to techniques for enabling decentralized learning of global language models (LMs). Remote processor(s) of a remote system can obtain a global LM that includes a global embedding ma...