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:
Apr. 04, 2023

Filed:

Oct. 01, 2020
Applicant:

Baidu Usa, Llc, Sunnyvale, CA (US);

Inventors:

Anuroop Sriram, Sunnyvale, CA (US);

Heewoo Jun, Sunnyvale, CA (US);

Sanjeev Satheesh, Sunnyvale, CA (US);

Adam Coates, Mountain View, CA (US);

Assignee:

Baidu USA LLC, Sunnyvale, CA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G10L 15/06 (2013.01); G06N 3/08 (2023.01); G10L 15/183 (2013.01); G06N 3/04 (2023.01); G06N 3/088 (2023.01); G10L 15/16 (2006.01);
U.S. Cl.
CPC ...
G10L 15/063 (2013.01); G06N 3/0445 (2013.01); G06N 3/0454 (2013.01); G06N 3/08 (2013.01); G06N 3/088 (2013.01); G10L 15/183 (2013.01); G06N 3/0481 (2013.01); G10L 15/16 (2013.01);
Abstract

Described herein are systems and methods for generating natural language sentences with Sequence-to-sequence (Seq2Seq) models with attention. The Seq2Seq models may be implemented in applications, such as machine translation, image captioning, and speech recognition. Performance has further been improved by leveraging unlabeled data, often in the form of a language models. Disclosed herein are 'Cold Fusion' architecture embodiments that leverage a pre-trained language model during training. The Seq2Seq models with Cold Fusion embodiments are able to better utilize language information enjoying faster convergence, better generalization, and almost complete transfer to a new domain while using less labeled training data.


Find Patent Forward Citations

Loading…