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:
Mar. 10, 2020

Filed:

Jun. 28, 2018
Applicant:

Microsoft Technology Licensing, Llc, Redmond, WA (US);

Inventors:

Minjia Zhang, Redmond, WA (US);

Xiaodong Liu, Beijing, CN;

Wenhan Wang, Redmond, WA (US);

Jianfeng Gao, Woodinville, WA (US);

Yuxiong He, Redmond, WA (US);

Assignee:
Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06F 17/27 (2006.01); G06F 16/33 (2019.01); G06F 16/901 (2019.01);
U.S. Cl.
CPC ...
G06F 17/2785 (2013.01); G06F 16/3347 (2019.01); G06F 16/9024 (2019.01);
Abstract

Systems, methods, and computer-executable instructions for approximating a softmax layer are disclosed. A small world graph that includes a plurality of nodes is constructed for a vocabulary of a natural language model. A context vector is transformed. The small world graph is searched using the transformed context vector to identify a top-K hypothesis. A distance from the context vector for each of the top-K hypothesis is determined. The distance is transformed to an original inner product space. A softmax distribution is computed for the softmax layer over the inner product space of the top-K hypothesis. The softmax layer is useful for determining a next word in a speech recognition or machine translation.


Find Patent Forward Citations

Loading…