US Patent Issued to Oracle International on Sept. 23 for "Efficient and accurate regional explanation technique for NLP models" (Canadian, American Inventors)

ALEXANDRIA, Va., Sept. 23 -- United States Patent no. 12,423,599, issued on Sept. 23, was assigned to Oracle International Corp. (Redwood Shores, Calif.).

"Efficient and accurate regional explanation technique for NLP models" was invented by Zahra Zohrevand (Vancouver, Canada), Tayler Hetherington (Vancouver, Canada), Karoon Rashedi Nia (Vancouver, Canada), Yasha Pushak (Vancouver, Canada), Sanjay Jinturkar (Santa Clara, Calif.) and Nipun Agarwal (Saratoga, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Herein are techniques for topic modeling and content perturbation that provide machine learning (ML) explainability (MLX) for natural language processing (NLP). A computer hosts an ML model that infers...