公开(公告)号：US10726831B2

公开(公告)日：2020-07-28

申请号：US14283017

申请日：2014-05-20

Applicant: Amazon Technologies, Inc.

Inventor： Giuseppe Di Fabbrizio ,  Shishir Sridhar Bharathi ,  Ying Shi ,  Lambert Mathias

IPC: G10L15/18 ,  G10L15/00 ,  G10L15/22 ,  G06F16/332 ,  G10L15/30 ,  G06F40/35

Abstract: Features are disclosed for processing and interpreting natural language, such as interpretations of user utterances, in multi-turn dialog interactions. Context information regarding interpretations of user utterances and system responses to the user utterances can be maintained. Subsequent user utterances can be interpreted using the context information, rather than being interpreted without context. In some cases, interpretations of subsequent user utterances can be merged with interpretations of prior user utterances using a rule-based framework. Rules may be defined to determine which interpretations may be merged and under what circumstances they may be merged.

公开(公告)号：US09953637B1

公开(公告)日：2018-04-24

申请号：US14225135

申请日：2014-03-25

Applicant: Amazon Technologies, Inc.

Inventor： Giuseppe Di Fabbrizio ,  Wei Chen ,  Benjamin Edward Lambert

IPC: G10L15/00 ,  G10L15/04 ,  G10L15/08

CPC classification number: G10L15/22 ,  G10L15/1815

Abstract: Features are disclosed for processing user utterances and applying user-supplied corrections to future user utterances. If a user utterance is determined to relate to a speech processing error that occurred when processing a previous utterance, information about the error or a correction thereto may be stored. Such information may be referred to as correction information. Illustratively, the correction information may be stored in a skip list. Subsequent utterances may be processed based at least partly on the correction information. For example, speech processing results generated from processing subsequent utterances that include a term associated with the error may be removed or re-scored in order to reduce or prevent the chance that an error will be repeated.

公开(公告)号：US20150340033A1

公开(公告)日：2015-11-26

申请号：US14283017

申请日：2014-05-20

Applicant: Amazon Technologies, Inc.

Inventor： Giuseppe Di Fabbrizio ,  Shishir Sridhar Bharathi ,  Ying Shi ,  Lambert Mathias

IPC: G10L15/18 ,  G10L15/00

Abstract: Features are disclosed for processing and interpreting natural language, such as interpretations of user utterances, in multi-turn dialog interactions. Context information regarding interpretations of user utterances and system responses to the user utterances can be maintained. Subsequent user utterances can be interpreted using the context information, rather than being interpreted without context. In some cases, interpretations of subsequent user utterances can be merged with interpretations of prior user utterances using a rule-based framework. Rules may be defined to determine which interpretations may be merged and under what circumstances they may be merged.

Abstract translation: 公开了用于处理和解释自然语言的特征，例如用户话语的解释，在多圈对话交互中。 可以保持关于用户话语的解释和对用户话语的系统响应的上下文信息。 可以使用上下文信息来解释随后的用户话语，而不是在没有上下文的情况下被解释。 在某些情况下，使用基于规则的框架，对后续用户话语的解释可以与先前用户话语的解释相结合。 可以定义规则来确定哪些解释可以合并，以及在什么情况下可以合并。