Context-sensitive generation of conversational responses

US10091140B2 · kind B2 · utility

Assignee

• MICROSOFT TECHNOLOGY LICENSING, LLC · US

Inventors

• Michel Galley · Seattle, US
• Alessandro Sordoni · Montréal, CA
• Christopher John Brockett · Bellevue, US
• Jianfeng Gao · Woodinville, US
• William B. Dolan · Kirkland, US
• Yangfeng Ji · Atlanta, US
• Michael Auli · Menlo Park, US
• Margaret Ann Mitchell · Seattle, US
• Jian-Yun Nie · Brossard, CA

Key dates

• Filing date: May 31, 2015
• Grant date: Oct 2, 2018
• Expiry date: May 10, 2036

Classification

• Technology area (CPC G): Physics
• CPC primary: G06N3/09
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

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.