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. 17, 2019

Filed:

Mar. 29, 2017
Applicant:

Mitsubishi Electric Research Laboratories, Inc., Cambridge, MA (US);

Inventors:

Chiori Hori, Lexington, MA (US);

Takaaki Hori, Lexington, MA (US);

John Hershey, Winchester, MA (US);

Tim Marks, Newton, MA (US);

Attorneys:
Primary Examiner:
Int. Cl.
CPC ...
G06K 9/00 (2006.01); G06K 9/46 (2006.01); G06N 3/04 (2006.01); G06F 17/28 (2006.01); G10L 25/30 (2013.01); G10L 25/57 (2013.01); G06F 16/783 (2019.01); H04N 21/439 (2011.01); H04N 21/2343 (2011.01); H04N 21/8549 (2011.01);
U.S. Cl.
CPC ...
G06K 9/00744 (2013.01); G06F 16/783 (2019.01); G06F 17/28 (2013.01); G06K 9/00718 (2013.01); G06K 9/4671 (2013.01); G06N 3/0445 (2013.01); G06N 3/0454 (2013.01); G10L 25/30 (2013.01); G10L 25/57 (2013.01); H04N 21/234336 (2013.01); H04N 21/4394 (2013.01); H04N 21/8549 (2013.01);
Abstract

A system for generating a word sequence includes one or more processors in connection with a memory and one or more storage devices storing instructions causing operations that include receiving first and second input vectors, extracting first and second feature vectors, estimating a first set of weights and a second set of weights, calculating a first content vector from the first set of weights and the first feature vectors, and calculating a second content vector, transforming the first content vector into a first modal content vector having a predetermined dimension and transforming the second content vector into a second modal content vector having the predetermined dimension, estimating a set of modal attention weights, generating a weighted content vector having the predetermined dimension from the set of modal attention weights and the first and second modal content vectors, and generating a predicted word using the sequence generator.


Find Patent Forward Citations

Loading…