公开(公告)号：WO2014204659A3

公开(公告)日：2014-12-24

申请号：PCT/US2014/041023

申请日：2014-06-05

Applicant: MICROSOFT CORPORATION

Inventor： SARIKAYA, Ruhi ,  BOIES, Daniel ,  HECK, Larry ,  ANASTASAKOS, Tasos

IPC: G06F17/27 ,  G10L15/18

Abstract: A method for enabling an application for Conversational Understanding (CU) using assets in a CU service, comprising: determining a domain for the application to use; receiving a selection of Application Programming Interfaces (APIs) that are associated with the domain to use in the application; automatically updating models for the CU service based on the selection of the APIs and the determined domain; and making the models available to the CU service.

公开(公告)号：WO2013169530A2

公开(公告)日：2013-11-14

申请号：PCT/US2013/038966

申请日：2013-05-01

Applicant: MICROSOFT CORPORATION

Inventor： SARIKAYA, Ruhi ,  BOIES, Daniel ,  CELIKYILMAZ, Fethiye Asli ,  DEORAS, Anoop K. ,  HAKKANI-TUR, Dilek Z. ,  HILLARD, Dustin Rigg ,  TUR, Gokhan ,  ALLEVA, Fileno A.

IPC: G06F17/28

CPC classification number: G06F17/289

Abstract: Processes capable of accepting linguistic input in one or more languages are generated by re-using existing linguistic components associated with a different anchor language, together with machine translation components that translate between the anchor language and the one or more languages. Linguistic input is directed to machine translation components that translate such input from its language into the anchor language. Those existing linguistic components are then utilized to initiate responsive processing and generate output. Optionally, the output is directed through the machine translation components. A language identifier can initially receive linguistic input and identify the language within which such linguistic input is provided to select an appropriate machine translation component. A hybrid process, comprising machine translation components and linguistic components associated with the anchor language, can also serve as an initiating construct from which a single language process is created over time.

Abstract translation: 通过重新使用与不同锚语言相关联的现有语言组件以及在锚语言和一种或多种语言之间进行翻译的机器翻译组件来生成能够接受一种或多种语言的语言输入的过程。 语言输入针对机器翻译组件，将这种输入从其语言转换为锚语言。 然后利用现有的语言分量来启动响应处理并产生输出。 可选地，输出被引导通过机器翻译组件。 语言标识符可以最初接收语言输入并且识别提供这种语言输入以选择适当的机器翻译组件的语言。 包括与锚语言相关联的机器翻译组件和语言组件的混合过程也可以用作随时间推移创建单个语言过程的起始构造。

公开(公告)号：WO2014120699A2

公开(公告)日：2014-08-07

申请号：PCT/US2014/013469

申请日：2014-01-29

Applicant: MICROSOFT CORPORATION

Inventor： SARIKAYA, Ruhi ,  DEORAS, Anoop ,  CELIKYILMAZ, Fethiye Asli ,  JANARDHANA, Ravikiran ,  BOIES, Daniel

IPC: G06F17/27

CPC classification number: G06F17/279 ,  G06F17/30672

Abstract: A scalable statistical language understanding (SLU) system uses a fixed number of understanding models that scale across domains and intents (i.e. single vs. multiple intents per utterance). For each domain added to the SLU system, the fixed number of existing models is updated to reflect the newly added domain. Information that is already included in the existing models and the corresponding training data may be re-used. The fixed models may include a domain detector model, an intent action detector model, an intent object detector model and a slot/entity tagging model. A domain detector identifies different domains identified within an utterance. All/portion of the detected domains are used to determine associated intent actions. For each determined intent action, one or more intent objects are identified. Slot/entity tagging is performed using the determined domains, intent actions, and intent object detector.

Abstract translation: 可扩展的统计语言理解（SLU）系统使用固定数量的理解模型来扩展域和意图（即每个话语的单个对多个意图）。 对于添加到SLU系统的每个域，将更新固定数量的现有模型以反映新添加的域。 已经包含在现有模型中的信息和相应的训练数据可能被重新使用。 固定模型可以包括域检测器模型，意图动作检测器模型，意图对象检测器模型和时隙/实体标签模型。 域检测器识别在话语内识别的不同域。 检测到的域的全部/部分用于确定相关联的意图动作。 对于每个确定的意图行为，识别一个或多个意图对象。 使用确定的域，意图动作和意图对象检测器执行插槽/实体标记。

公开(公告)号：WO2014204655A1

公开(公告)日：2014-12-24

申请号：PCT/US2014/041014

申请日：2014-06-05

Applicant: MICROSOFT CORPORATION

Inventor： BOIES, Daniel ,  HECK, Larry ,  ANASTASAKOS, Tasos ,  SARIKAYA, Ruhi

IPC: G06F17/27

CPC classification number: G10L15/22 ,  G06F17/2785 ,  G10L17/22

Abstract: Environmental conditions, along with other information, are used to adjust a response of a conversational dialog system. The environmental conditions may be used at different times within the conversational dialog system. For example, the environmental conditions can be used to adjust the dialog manager's output (e.g., the machine action). The dialog state information that is used by the dialog manager includes environmental conditions for the current turn in the dialog as well as environmental conditions for one or more past turns in the dialog. The environmental conditions can also be used after receiving the machine action to adjust the response that is provided to the user. For example, the environmental conditions may affect the machine action that is determined as well as how the action is provided to the user. The dialog manager and the response generation components in the conversational dialog system each use the available environmental conditions.

Abstract translation: 环境条件以及其他信息用于调整会话对话系统的响应。 环境条件可以在会话对话系统内的不同时间使用。 例如，可以使用环境条件来调整对话管理器的输出（例如，机器动作）。 对话管理器使用的对话状态信息包括对话框中当前转弯的环境条件以及对话框中一个或多个过去转弯的环境条件。 环境条件也可以在接收机器动作后使用，以调整提供给用户的响应。 例如，环境条件可能影响确定的机器动作以及如何向用户提供动作。 会话对话系统中的对话管理器和响应生成组件都使用可用的环境条件。