利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

13 条记录 (耗时 0.017 秒)

    Representation Learning Using Multi-Task Deep Neural Networks
    2.
    发明申请
    Representation Learning Using Multi-Task Deep Neural Networks 审中-公开
    使用多任务深层神经网络的表征学习

    公开(公告)号：US20170032035A1

    公开(公告)日：2017-02-02

    申请号：US14811808

    申请日：2015-07-28

    申请人： Microsoft Technology Licensing, LLC

    发明人： Jianfeng Gao ,  Li Deng ,  Xiaodong He ,  Ye-Yi Wang ,  Kevin Duh ,  Xiaodong Liu

    IPC分类号： G06F17/30 ,  G06N3/08

    CPC分类号： G06N3/08 ,  G06F17/3069 ,  G06F17/30867

    摘要： A system may comprise one or more processors and memory storing instructions that, when executed by one or more processors, configure one or more processors to perform a number of operations or tasks, such as receiving a query or a document, and mapping the query or the document into a lower dimensional representation by performing at least one operational layer that shares at least two disparate tasks.

    摘要翻译： 系统可以包括一个或多个处理器和存储器存储指令，当由一个或多个处理器执行时，配置一个或多个处理器来执行多个操作或任务，诸如接收查询或文档，以及映射查询或 通过执行共享至少两个不同任务的至少一个操作层来将文档转换成较低维度的表示。

    Extension of Third Party Application Functionality for Intent Determination
    3.
    发明申请
    Extension of Third Party Application Functionality for Intent Determination 审中-公开
    扩展第三方应用功能的意图确定

    公开(公告)号：US20160239568A1

    公开(公告)日：2016-08-18

    申请号：US14622815

    申请日：2015-02-13

    申请人： Microsoft Technology Licensing, LLC

    发明人： Alan Packer ,  Ravi Bikkula ,  Ye-Yi Wang

    IPC分类号： G06F17/30

    摘要： Intent determination as a service (IaaS) is disclosed. A third party application may be provided access to an IaaS service. The third party application and the IaaS system may exchange or be provided registration data and information that allow configuration of data and interfaces used in provision of IaaS to the third party application. A query received as input at the third party application may be sent to the IaaS system and the intent of a query may be determined and indicated in a query response sent back to the third party application. A third party application may also interface with a device client application integrated into the operating system of a device as part of accessing an IaaS system. Use of IaaS for queries associated with or relevant to third party applications may extend the capabilities of the third party applications and device client applications.

    摘要翻译： 意向性确定即服务（IaaS）被披露。 可以向第三方应用程序提供对IaaS服务的访问。 第三方应用程序和IaaS系统可以交换或提供注册数据和信息，允许将为IaaS提供的数据和接口配置到第三方应用程序。 在第三方应用程序中作为输入接收的查询可以被发送到IaaS系统，并且可以在发回到第三方应用的查询响应中确定并指示查询的意图。 作为访问IaaS系统的一部分，第三方应用程序还可以与集成到设备的操作系统中的设备客户端应用程序接口。 对于与第三方应用相关或与之相关的查询，IaaS的使用可能会扩展第三方应用程序和设备客户端应用程序的功能。

    Exploiting structured content for unsupervised natural language semantic parsing
    6.
    发明授权
    Exploiting structured content for unsupervised natural language semantic parsing 有权

    公开(公告)号：US10235358B2

    公开(公告)日：2019-03-19

    申请号：US13773269

    申请日：2013-02-21

    申请人： Microsoft Technology Licensing, LLC

    发明人： Gokhan Tur ,  Dilek Hakkani-Tur ,  Larry Heck ,  Minwoo Jeong ,  Ye-Yi Wang

    IPC分类号： G06F17/28 ,  G06F17/27

    摘要： Structured web pages are accessed and parsed to obtain implicit annotation for natural language understanding tasks. Search queries that hit these structured web pages are automatically mined for information that is used to semantically annotate the queries. The automatically annotated queries may be used for automatically building statistical unsupervised slot filling models without using a semantic annotation guideline. For example, tags that are located on a structured web page that are associated with the search query may be used to annotate the query. The mined search queries may be filtered to create a set of queries that is in a form of a natural language query and/or remove queries that are difficult to parse. A natural language model may be trained using the resulting mined queries. Some queries may be set aside for testing and the model may be adapted using in-domain sentences that are not annotated. The models may be tested using these implicitly annotated natural-language-like queries in an unsupervised fashion.

    MULTI-DOMAIN JOINT SEMANTIC FRAME PARSING
    7.
    发明申请
    MULTI-DOMAIN JOINT SEMANTIC FRAME PARSING 审中-公开

    公开(公告)号：US20170372199A1

    公开(公告)日：2017-12-28

    申请号：US15228990

    申请日：2016-08-04

    申请人： Microsoft Technology Licensing, LLC

    发明人： Dilek Z Hakkani-Tur ,  Asli Celikyilmaz ,  Yun-Nung Chen ,  Li Deng ,  Jianfeng Gao ,  Gokhan Tur ,  Ye-Yi Wang

    IPC分类号： G06N3/08 ,  G06N3/04

    CPC分类号： G06N3/08 ,  G06N3/0445 ,  G10L15/16 ,  G10L15/1822 ,  G10L15/22

    摘要： A processing unit can train a model as a joint multi-domain recurrent neural network (JRNN), such as a bi-directional recurrent neural network (bRNN) and/or a recurrent neural network with long-short term memory (RNN-LSTM) for spoken language understanding (SLU). The processing unit can use the trained model to, e.g., jointly model slot filling, intent determination, and domain classification. The joint multi-domain model described herein can estimate a complete semantic frame per query, and the joint multi-domain model enables multi-task deep learning leveraging the data from multiple domains. The joint multi-domain recurrent neural network (JRNN) can leverage semantic intents (such as, finding or identifying, e.g., a domain specific goal) and slots (such as, dates, times, locations, subjects, etc.) across multiple domains.

    Automatic task extraction and calendar entry
    8.
    发明授权
    Automatic task extraction and calendar entry 有权

    公开(公告)号：US11328259B2

    公开(公告)日：2022-05-10

    申请号：US17167277

    申请日：2021-02-04

    申请人： Microsoft Technology Licensing, LLC

    发明人： Michael Gamon ,  Saliha Azzam ,  Yizheng Cai ,  Nicholas Caldwell ,  Ye-Yi Wang

    IPC分类号： G06Q10/10

    摘要： Automatically detected and identified tasks and calendar items from electronic communications may be populated into one or more tasks applications and calendaring applications. Text content retrieved from one or more electronic communications may be extracted and parsed for determining whether keywords or terms contained in the parsed text may lead to a classification of the text content or part of the text content as a task. Identified tasks may be automatically populated into a tasks application. Similarly, text content from such sources may be parsed for keywords and terms that may be identified as indicating calendar items, for example, meeting requests. Identified calendar items may be automatically populated into a calendar application as a calendar entry.

    Extension of third party application functionality for intent determination
    9.
    发明授权
    Extension of third party application functionality for intent determination 有权

    公开(公告)号：US10762143B2

    公开(公告)日：2020-09-01

    申请号：US14622815

    申请日：2015-02-13

    申请人： Microsoft Technology Licensing, LLC

    发明人： Alan Packer ,  Ravi Bikkula ,  Ye-Yi Wang

    IPC分类号： G06F7/00 ,  G06F16/00 ,  G06F16/951

    摘要： Intent determination as a service (IaaS) is disclosed. A third party application may be provided access to an IaaS service. The third party application and the IaaS system may exchange or be provided registration data and information that allow configuration of data and interfaces used in provision of IaaS to the third party application. A query received as input at the third party application may be sent to the IaaS system and the intent of a query may be determined and indicated in a query response sent back to the third party application. A third party application may also interface with a device client application integrated into the operating system of a device as part of accessing an IaaS system. Use of IaaS for queries associated with or relevant to third party applications may extend the capabilities of the third party applications and device client applications.