The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Sep. 01, 2026

Filed:

May. 28, 2024
Applicant:

Amazon Technologies, Inc., Seattle, WA (US);

Inventors:

Jinglun Cai, Seattle, WA (US);

Jie Yuan, Bellevue, WA (US);

Monica Lakshmi Sunkara, San Francisco, CA (US);

Hang Su, Redmond, WA (US);

Saab Mansour, San Jose, CA (US);

Igor Shalyminov, San Jose, CA (US);

Katrin Kirchhoff, Seattle, WA (US);

Assignee:

Amazon Technologies, Inc., Seattle, WA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06F 40/30 (2020.01); G06F 16/3329 (2025.01); G06F 16/334 (2025.01); G06F 16/34 (2019.01); G06F 40/35 (2020.01);
U.S. Cl.
CPC ...
G06F 40/30 (2020.01); G06F 16/3329 (2019.01); G06F 16/3346 (2019.01); G06F 16/345 (2019.01); G06F 40/35 (2020.01);
Abstract

Techniques for text generation refinement are described. In some examples, a predicted text output is generated, wherein the predicted text output is selected from a plurality of predicted texts generated in response to the request, wherein the generating comprises: predicting a plurality of predicted texts using at least one machine learning model, scoring each of the plurality of predicted texts using at least one of intra-sample scoring and inter-sample scoring, computing a composite score for each of the plurality of predicted texts from the scores, ranking the plurality of predicted texts based at least in part the composite score, and selecting at least a highest ranked predicted text of the plurality of predicted texts as the predicted text output.


Find Patent Forward Citations

Loading…