US Patent Issued to International Business Machines on March 18 for "Generating unique word embeddings for jargon-specific tabular data for neural network training and usage" (New York Inventors)

ALEXANDRIA, Va., March 19 -- United States Patent no. 12,254,265, issued on March 18, was assigned to International Business Machines Corp. (Armonk, N.Y.).

"Generating unique word embeddings for jargon-specific tabular data for neural network training and usage" was invented by Bhavna Agrawal (Armonk, N.Y.), Elham Khabiri (Briarcliff Manor, N.Y.), Yingjie Li (Chappaqua, N.Y.) and Pranav Girish Sankhe (Buffalo, N.Y.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Tabular data is accessed that contains multiple entries of alphanumeric data. Multiple tokens are generated of the multiple entries of alphanumeric data using a tokenization process. The tokenization process maintains jargon-specific features of the a...