Patents by Inventor Margaret Ann MITCHELL
Margaret Ann MITCHELL has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 10997226Abstract: Examples described herein provide a digital assistant crafting a response based on target sentiment identification from user input. The digital assistant receives unstructured data input and identifies a segment of the input that includes a facet item. A sentiment associated with the facet item in the segment is identified and classified to identify a targeted sentiment directed towards the facet item. A response is generated based on the targeted sentiment and the facet item.Type: GrantFiled: May 21, 2015Date of Patent: May 4, 2021Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Melissa Nicole Lim, Margaret Ann Mitchell, Piali Choudhury
-
Patent number: 10536402Abstract: 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.Type: GrantFiled: August 24, 2018Date of Patent: January 14, 2020Assignee: Microsoft Technology Licensing, LLCInventors: Michel Galley, Alessandro Sordoni, Christopher John Brockett, Jianfeng Gao, William Brennan Dolan, Yangfeng Ji, Michael Auli, Margaret Ann Mitchell, Jian-Yun Nie
-
Patent number: 10446142Abstract: Examples described herein dynamically personalize a digital assistant for a specific user, creating a personal connection between the digital assistant and the user. The digital assistant accesses user activity and generates queries based on the user activity. The digital assistant facilitates natural language conversations as machine learning sessions between the digital assistant and the user using the one or more queries to learn the user's preferences and receives user input from the user during the learning session in response to the queries. The digital assistant dynamically updates a personalized profile for the user based on the user input during the natural language conversations.Type: GrantFiled: May 20, 2015Date of Patent: October 15, 2019Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Melissa Nicole Lim, Margaret Ann Mitchell, Christopher Brian Quirk
-
Publication number: 20180367475Abstract: 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.Type: ApplicationFiled: August 24, 2018Publication date: December 20, 2018Inventors: Michel GALLEY, Alessandro SORDONI, Christopher John BROCKETT, Jianfeng GAO, William Brennan DOLAN, Yangfeng JI, Michael AULI, Margaret Ann MITCHELL, Jian-Yun NIE
-
Patent number: 10091140Abstract: 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.Type: GrantFiled: May 31, 2015Date of Patent: October 2, 2018Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Michel Galley, Alessandro Sordoni, Christopher John Brockett, Jianfeng Gao, William Brennan Dolan, Yangfeng Ji, Michael Auli, Margaret Ann Mitchell, Jian-Yun Nie
-
Patent number: 9967211Abstract: 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.Type: GrantFiled: May 31, 2015Date of Patent: May 8, 2018Assignee: Microsoft Technology Licensing, LLCInventors: Michel Galley, Alessandro Sordoni, Christopher John Brockett, Jianfeng Gao, William Brennan Dolan, Yangfeng Ji, Michael Auli, Margaret Ann Mitchell, Christopher Brian Quirk
-
Publication number: 20160352656Abstract: 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.Type: ApplicationFiled: May 31, 2015Publication date: December 1, 2016Inventors: Michel GALLEY, Alessandro SORDONI, Christopher John BROCKETT, Jianfeng GAO, III, William Brennan DOLAN, Yangfeng JI, Michael AULI, Margaret Ann MITCHELL, Jian-Yun NIE
-
Publication number: 20160352657Abstract: 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.Type: ApplicationFiled: May 31, 2015Publication date: December 1, 2016Inventors: Michel GALLEY, Alessandro SORDONI, Christopher John BROCKETT, Jianfeng GAO, III, William Brennan DOLAN, Yangfeng JI, Michael AULI, Margaret Ann MITCHELL, Christopher Brian QUIRK
-
Publication number: 20160342317Abstract: Examples described herein dynamically personalize a digital assistant for a specific user, creating a personal connection between the digital assistant and the user. The digital assistant accesses user activity and generates queries based on the user activity. The digital assistant facilitates natural language conversations as machine learning sessions between the digital assistant and the user using the one or more queries to learn the user's preferences and receives user input from the user during the learning session in response to the queries. The digital assistant dynamically updates a personalized profile for the user based on the user input during the natural language conversations.Type: ApplicationFiled: May 20, 2015Publication date: November 24, 2016Inventors: Melissa Nicole LIM, Margaret Ann MITCHELL, Christopher Brian QUIRK
-
Publication number: 20160342683Abstract: Examples described herein provide a digital assistant crafting a response based on target sentiment identification from user input. The digital assistant receives unstructured data input and identifies a segment of the input that includes a facet item. A sentiment associated with the facet item in the segment is identified and classified to identify a targeted sentiment directed towards the facet item. A response is generated based on the targeted sentiment and the facet item.Type: ApplicationFiled: May 21, 2015Publication date: November 24, 2016Inventors: Melissa Nicole LIM, Margaret Ann MITCHELL, Piali CHOUDHURY