发明名称 |
CONTEXT-SENSITIVE GENERATION OF CONVERSATIONAL RESPONSES |
摘要 |
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. |
申请公布号 |
US2016352656(A1) |
申请公布日期 |
2016.12.01 |
申请号 |
US201514726562 |
申请日期 |
2015.05.31 |
申请人 |
MICROSOFT TECHNOLOGY LICENSING, LLC |
发明人 |
GALLEY Michel;SORDONI Alessandro;BROCKETT Christopher John;GAO, III Jianfeng;DOLAN William Brennan;JI Yangfeng;AULI Michael;MITCHELL Margaret Ann;NIE Jian-Yun |
分类号 |
H04L12/58 |
主分类号 |
H04L12/58 |
代理机构 |
|
代理人 |
|
主权项 |
1. A computer-implemented method for state-free generation of context-sensitive conversational responses, said method comprising:
accessing conversational context data from a set of context data sources associated with a user, by a response generation engine trained on a plurality of context-message-response n-tuples extracted from at least one source of conversational data, the conversational context data corresponding to a user generated message associated with a current conversation; and generating a context-sensitive response to the user generated message, by the response generation engine, based on the conversational context data and the user generated message. |
地址 |
Redmond WA US |