ALEXANDRIA, Va., Feb. 17 -- United States Patent no. 12,554,937, issued on Feb. 17, was assigned to International Business Machines Corp. (Armonk, N.Y.).
"Few shot incremental learning for named entity recognition" was invented by Ritesh Kumar (Morristown, N.J.), Saurabh Goyal (Jersey City, N.J.) and Ashish Verma (Nanuet, N.Y.).
According to the abstract* released by the U.S. Patent & Trademark Office: "A method, computer system, and a computer program product for classification training are provided. A deep learning model is trained with a first dataset that includes annotated samples that include a first and second class. Last hidden state features corresponding to respective tokens from prototypes of the first and second class are save...