Song Wang

US Patent:

20220392434, Dec 8, 2022

Filed:

Jun 8, 2021

Appl. No.:

17/342490

Inventors:

- Redmond WA, US
Yarin KUPER - Tel-Aviv, IL
Royi RONEN - Tel Aviv, IL
Song WANG - Bellevue WA, US
Olga GOLDENBERG - Tel Aviv, IL
Shimrit Rada BEMIS - Tel Aviv, IL
Erez ALTUS - Tel-Aviv, IL
Yi MAO - Redmond WA, US
Weizhu CHEN - Kirkland WA, US

International Classification:

G10L 15/06
G06N 20/00

Abstract:

The disclosure herein describes reducing training bias in outputs generated by a generative language model. A communication segment associated with a communication is obtained by at least one processor of a generative language model. An output value associated with the communication segment is generated by the generative language model. The output value is mapped to a set of training bias values associated with the generative language model and based on the mapping of the output value to a training bias value of the set of training bias values, an alternative output value is generated. The alternative output value is used in a generated segment output for the communication segment. The accuracy of segment outputs generated by the generative language model is improved through reducing or eliminating its training biases.