ALEXANDRIA, Va., May 26 -- United States Patent no. 12,639,519, issued on May 26, was assigned to Microsoft Technology Licensing LLC (Redmond, Wash.).

"Training masked language models based on partial sequences of tokens" was invented by Andy Wagner (Cupertino, Calif.), Tiyasa Mitra (San Jose, Calif.) and Fanny Nina Paravecino (San Jose, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Embodiments of the present disclosure include systems and methods for training masked language models based on partial sequences of tokens. A sequence of tokens for training a transformer model is received. A defined proportion of the sequence of tokens is selected. Each value of the defined proportion of the sequence of ...