18819441. MULTI-FEATURE BALANCING FOR NATURAL LANGUAGE PROCESSORS (Oracle International Corporation)

MULTI-FEATURE BALANCING FOR NATURAL LANGUAGE PROCESSORS

Organization Name

Oracle International Corporation

Inventor(s)

Thanh Long Duong of Melbourne (AU)

Vishal Vishnoi of Redwood City CA (US)

Mark Edward Johnson of Sydney (AU)

Elias Luqman Jalaluddin of Seattle WA (US)

Tuyen Quang Pham of Melbourne (AU)

Cong Duy Vu Hoang of Melbourne (AU)

Poorya Zaremoodi of Melbourne (AU)

Srinivasa Phani Kumar Gadde of Fremont CA (US)

Aashna Devang Kanuga of Foster City CA (US)

Zikai Li of Redwood City CA (US)

Yuanxu Wu of Foster City CA (US)

MULTI-FEATURE BALANCING FOR NATURAL LANGUAGE PROCESSORS

This abstract first appeared for US patent application 18819441 titled 'MULTI-FEATURE BALANCING FOR NATURAL LANGUAGE PROCESSORS

Original Abstract Submitted

A method includes receiving an indication of a first coverage value corresponding to a desired overlap between a dataset of natural language phrases and a training dataset for training a machine learning model; determining a second coverage value corresponding to a measured overlap between the dataset of natural language phrases and the training dataset; determining a coverage delta value based on a comparison between the first coverage value and the second coverage value; modifying, based on the coverage delta value, the dataset of natural language phrases; and processing, utilizing a machine learning model including the modified dataset of natural language phrases, an input dataset including a set of input features. The machine learning model processes the input dataset based at least in part on the dataset of natural language phrases to generate an output dataset.