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:
Jul. 30, 2019

Filed:

Sep. 07, 2016
Applicant:

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

Inventors:

Yun-Nung Chen, Bellevue, WA (US);

Dilek Z. Hakkani-Tur, Los Altos, CA (US);

Gokhan Tur, Redmond, WA (US);

Asli Celikyilmaz, Kirkland, WA (US);

Jianfeng Gao, Woodinville, WA (US);

Li Deng, Redmond, WA (US);

Assignee:
Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06F 17/27 (2006.01); G10L 15/18 (2013.01); G10L 15/16 (2006.01);
U.S. Cl.
CPC ...
G06F 17/2785 (2013.01); G06F 17/2705 (2013.01); G10L 15/16 (2013.01); G10L 15/1822 (2013.01);
Abstract

Systems and methods for determining knowledge-guided information for a recurrent neural networks (RNN) to guide the RNN in semantic tagging of an input phrase are presented. A knowledge encoding module of a Knowledge-Guided Structural Attention Process (K-SAP) receives an input phrase and, in conjunction with additional sub-components or cooperative components generates a knowledge-guided vector that is provided with the input phrase to the RNN for linguistic semantic tagging. Generating the knowledge-guided vector comprises at least parsing the input phrase and generating a corresponding hierarchical linguistic structure comprising one or more discrete sub-structures. The sub-structures may be encoded into vectors along with attention weighting identifying those sub-structures that have greater importance in determining the semantic meaning of the input phrase.


Find Patent Forward Citations

Loading…