发明名称 GENERATION OF LANGUAGE UNDERSTANDING SYSTEMS AND METHODS
摘要 Domain-specific language understanding models that may be built, tested and improved quickly and efficiently are provided. Methods, systems and devices are provided that enable a developer to build user intent detection models, language entity extraction models, and language entity resolution models quickly and without specialized machine learning knowledge. These models may be built and implemented via single model systems that enable the models to be built in isolation or in an end-to-end pipeline system that enables the models to be built and improved in a simultaneous manner.
申请公布号 US2016196820(A1) 申请公布日期 2016.07.07
申请号 US201514678315 申请日期 2015.04.03
申请人 Microsoft Technology Licensing, LLC. 发明人 Williams Jason Douglas;Niraula Nobal Bikram;Dasigi Pradeep;Lakshmiratan Aparna;Zweig Geoffrey G.;Kolobov Andrey;Garcia Jurado Suarez Carlos;Chickering David Maxwell
分类号 G10L15/00;G10L15/18;G10L15/07 主分类号 G10L15/00
代理机构 代理人
主权项 1. A method for providing language understanding, comprising: receiving an utterance; building, by a computer, a user intent detection model based on one or more words contained in the received utterance, the user intent detection model for determining user intent in a subsequent received utterance; building, by a computer, an entity extraction model based on one or more words contained in the received utterance for finding language entities in the subsequent received utterance; applying the user intent detection model and the entity extraction model against the received utterance; and automatically generating labeling for a user intent and for the one or more language entities determined from the received utterance.
地址 Redmond WA US