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.
Patent No.:
Date of Patent:
Feb. 14, 2023
Filed:
Oct. 25, 2019
Applicant:
Salesforce.com, Inc., San Francisco, CA (US);
Inventors:
Stephen Joseph Merity, San Francisco, CA (US);
Caiming Xiong, Mountain View, CA (US);
James Bradbury, San Francisco, CA (US);
Richard Socher, Menlo Park, CA (US);
Assignee:
salesforce.com, inc., San Francisco, CA (US);
Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06N 3/04 (2006.01); G06N 3/084 (2023.01); G06F 40/284 (2020.01); G06N 3/08 (2023.01); G06N 7/00 (2023.01);
U.S. Cl.
CPC ...
G06N 3/0445 (2013.01); G06F 40/284 (2020.01); G06N 3/0454 (2013.01); G06N 3/0472 (2013.01); G06N 3/08 (2013.01); G06N 3/084 (2013.01); G06N 7/005 (2013.01);
Abstract
The technology disclosed provides a so-called 'pointer sentinel mixture architecture' for neural network sequence models that has the ability to either reproduce a token from a recent context or produce a token from a predefined vocabulary. In one implementation, a pointer sentinel-LSTM architecture achieves state of the art language modeling performance of 70.9 perplexity on the Penn Treebank dataset, while using far fewer parameters than a standard softmax LSTM.