US Patent Issued to Salesforce on May 27 for "Generative language model for few-shot aspect-based sentiment analysis" (California Inventors)

ALEXANDRIA, Va., June 17 -- United States Patent no. 12,314,673, issued on May 27, was assigned to Salesforce Inc. (San Francisco).

"Generative language model for few-shot aspect-based sentiment analysis" was invented by Ehsan Hosseini-Asl (Palo Alto, Calif.) and Wenhao Liu (Redwood City, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Sentiment analysis is a task in natural language processing. The embodiments are directed to using a generative language model to extract an aspect term, aspect category and their corresponding polarities. The generative language model may be trained as a single, joint, and multi-task model. The single-task generative language model determines a term polarity from the as...