Margaret Patricia Mitchell

US Patent:

20180367475, Dec 20, 2018

Filed:

Aug 24, 2018

Appl. No.:

16/112611

Inventors:

- Redmond WA, US
Alessandro SORDONI - Montreal, CA
Christopher John BROCKETT - Bellevue WA, US
Jianfeng GAO - Woodinville WA, US
William Brennan DOLAN - Kirkland WA, US
Yangfeng JI - Atlanta GA, US
Michael AULI - Menlo Park CA, US
Margaret Ann MITCHELL - Seattle WA, US
Jian-Yun NIE - Brossard, CA

International Classification:

H04L 12/58
G06N 3/04
G06F 17/28

Abstract:

Examples are generally directed towards context-sensitive generation of conversational responses. Context-message-response n-tuples are extracted from at least one source of conversational data to generate a set of training context-message-response n-tuples. A response generation engine is trained on the set of training context-message-response n-tuples. The trained response generation engine automatically generates a context-sensitive response based on a user generated input message and conversational context data. A digital assistant utilizes the trained response generation engine to generate context-sensitive, natural language responses that are pertinent to user queries.

US Patent:

20180261211, Sep 13, 2018

Filed:

May 14, 2018

Appl. No.:

15/978892

Inventors:

- Redmond WA, US
Margaret Mitchell - Redmond WA, US
Jay Banerjee - Redmond WA, US
Pallavi Choudhury - Redmond WA, US
Susan Hendrich - Redmond WA, US
Rebecca Mason - Redmond WA, US
Ron Owens - Redmond WA, US
Mouni Reddy - Redmond WA, US
Yaxiao Song - Redmond WA, US
Kristina Toutanova - Redmond WA, US
Liang Xu - Redmond WA, US
Xuetao Yin - Redmond WA, US

Assignee:

Microsoft Technology Licensing, LLC - Redmond WA

International Classification:

G10L 15/08
G06N 7/00
G06F 17/27
G06N 99/00
G06F 17/28
G06F 17/30
G06F 3/048
G06Q 30/02

Abstract:

A “Facet Recommender” creates conversational recommendations for facets of particular conversational topics, and optionally for things associated with those facets, from consumer reviews or other social media content. The Facet Recommender applies a machine-learned facet model and optional sentiment-model, to identify facets associated with spans or segments of the content and to determine neutral, positive, or negative consumer sentiment associated with those facets and, optionally, things associated with those facets. These facets are selected by the facet model from a list or set of manually defined or machine-learned facets for particular conversational topic types. The Facet Recommender then generates new conversational utterances (i.e., short neutral, positive or negative suggestions) about particular facets based on the sentiments associated with those facets. In various implementations, utterances are fit to one or more predefined conversational frameworks. Further, responses or suggestions provided as utterances may be personalized to individual users.

US Patent:

20170061250, Mar 2, 2017

Filed:

Aug 28, 2015

Appl. No.:

14/839430

Inventors:

- Redmond WA, US
Xiaodong He - Sammamish WA, US
Saurabh Gupta - Berkeley CA, US
Geoffrey G. Zweig - Sammamish GA, US
Forrest Iandola - Berkeley CA, US
Li Deng - Redmond WA, US
Hao Fang - Seattle WA, US
Margaret A. Mitchell - Seattle WA, US
John C. Platt - Bellevue WA, US
Rupesh Kumar Srivastava - Lugano, CH

International Classification:

G06K 9/62
G06F 17/27
G06K 9/00
G06K 9/52
G06T 7/60

Abstract:

Disclosed herein are technologies directed to discovering semantic similarities between images and text, which can include performing image search using a textual query, performing text search using an image as a query, and/or generating captions for images using a caption generator. A semantic similarity framework can include a caption generator and can be based on a deep multimodal similar model. The deep multimodal similarity model can receive sentences and determine the relevancy of the sentences based on similarity of text vectors generated for one or more sentences to an image vector generated for an image. The text vectors and the image vector can be mapped in a semantic space, and their relevance can be determined based at least in part on the mapping. The sentence associated with the text vector determined to be the most relevant can be output as a caption for the image.

US Patent:

20160352656, Dec 1, 2016

Filed:

May 31, 2015

Appl. No.:

14/726562

Inventors:

- Redmond WA, US
Alessandro SORDONI - Montreal, CA
Christopher John BROCKETT - Bellevue WA, US
Jianfeng GAO, III - Woodinville WA, US
William Brennan DOLAN - Kirkland WA, US
Yangfeng JI - Atlanta GA, US
Michael AULI - Menlo Park CA, US
Margaret Ann MITCHELL - Seattle WA, US
Jian-Yun NIE - Brossard, CA

International Classification:

H04L 12/58

Abstract:

Examples are generally directed towards context-sensitive generation of conversational responses. Context-message-response n-tuples are extracted from at least one source of conversational data to generate a set of training context-message-response n-tuples. A response generation engine is trained on the set of training context-message-response n-tuples. The trained response generation engine automatically generates a context-sensitive response based on a user generated input message and conversational context data. A digital assistant utilizes the trained response generation engine to generate context-sensitive, natural language responses that are pertinent to user queries.

US Patent:

20160352657, Dec 1, 2016

Filed:

May 31, 2015

Appl. No.:

14/726569

Inventors:

- Redmond WA, US
Alessandro SORDONI - Montreal, CA
Christopher John BROCKETT - Bellevue WA, US
Jianfeng GAO, III - Woodinville WA, US
William Brennan DOLAN - Kirkland WA, US
Yangfeng JI - Atlanta GA, US
Michael AULI - Menlo Park CA, US
Margaret Ann MITCHELL - Seattle WA, US
Christopher Brian QUIRK - Seattle WA, US

International Classification:

H04L 12/58

Abstract:

Examples are generally directed towards automatic assessment of machine generated conversational responses. Context-message-response n-tuples are extracted from at least one source of conversational data to generate a set of multi-reference responses. A response in the set of multi-reference responses includes it context-message data pair and rating. The rating indicates a quality of the response relative to the context-message data pair. A response assessment engine generates a metric score for a machine-generated response based on an assessment metric and the set of multi-reference responses. The metric score indicates a quality of the machine-generated conversational response relative to a user-generated message and a context of the user-generated message. A response generation system of a computing device, such as a digital assistant, is optimized and adjusted based on the metric score to improve the accuracy, quality, and relevance of responses output to the user.