公开(公告)号：WO2016109307A3

公开(公告)日：2016-10-06

申请号：PCT/US2015067238

申请日：2015-12-22

Applicant: MICROSOFT TECHNOLOGY LICENSING LLC

Inventor： ROBICHAUD JEAN-PHILIPPE ,  SARIKAYA RUHI

IPC: G06F17/30 ,  G06F17/27 ,  G10L15/00

CPC classification number: G06F17/278 ,  G06F17/279 ,  G06F17/30646 ,  G06F17/30654 ,  G06F17/30657 ,  G06F17/30663 ,  G06F17/30666 ,  G06F17/30684 ,  G06F17/30693 ,  G10L15/22

Abstract: Methods and systems are provided for discriminating ambiguous expressions to enhance user experience. For example, a natural language expression may be received by a speech recognition component (402). The natural language expression may include at least one of words, terms, and phrases of text. A dialog hypothesis set from the natural language expression may be created by using contextual information (404). In some cases, the dialog hypothesis set has at least two dialog hypotheses. A plurality of dialog responses may be generated for the dialog hypothesis set (406). The dialog hypothesis set may be ranked based on an analysis of the plurality of the dialog responses (408). An action may be performed based on ranking the dialog hypothesis set (410).

Abstract translation: 提供方法和系统用于区分不明确的表达以增强用户体验。 例如，自然语言表达可以由语音识别组件（402）接收。 自然语言表达可以包括文本的单词，术语和短语中的至少一个。 可以通过使用上下文信息来创建从自然语言表达式设置的对话假说（404）。 在某些情况下，对话假设集至少有两个对话假设。 可以为对话假设组（406）生成多个对话响应。 可以基于对多个对话响应的分析（408）对对话假设集进行排名。 可以基于对对话假设集合（410）的排序来执行动作。