Method and System for Entity Linking
    1.
    发明申请
    Method and System for Entity Linking 审中-公开
    实体链接的方法和系统

    公开(公告)号:US20160189047A1

    公开(公告)日:2016-06-30

    申请号:US14585315

    申请日:2014-12-30

    Applicant: Yahoo! Inc.

    Abstract: The present teaching relates to entity linking. In one example, a text string is received. The text string is segmented to obtain a segmentation with a set of one or more segments of the text string. A set of entities are identified, with respect to the one or more segments, from a plurality of entities as linked to the one or more segments. The identifying is in accordance with a probabilistic model based on surface form information associated with the plurality of entities.

    Abstract translation: 本教学与实体联系有关。 在一个示例中,接收文本串。 文本字符串被分段以获得具有文本串的一个或多个段的集合的分割。 相对于一个或多个段,从与所述一个或多个段相关联的多个实体中识别一组实体。 识别符合基于与多个实体相关联的表面形式信息的概率模型。

    GENERATING USER RECOMMENDATIONS
    3.
    发明申请
    GENERATING USER RECOMMENDATIONS 有权
    产生用户建议

    公开(公告)号:US20160179835A1

    公开(公告)日:2016-06-23

    申请号:US14573756

    申请日:2014-12-17

    Applicant: Yahoo! Inc.

    CPC classification number: G06F17/3097 G06F17/30734 G06F17/30867 G06N99/005

    Abstract: Briefly, embodiments of methods and/or systems of providing relevant and diverse recommendations are disclosed. For one embodiment, as an example, a system may extract structured and/or semi-structured parameters from web resources obtained from interaction logs comprising records of browsing sessions. Content from extracted parameters may be compared, using an ontology, to find relationships among web resources and query resources.

    Abstract translation: 简而言之,公开了提供相关和多样化建议的方法和/或系统的实施例。 对于一个实施例,作为示例,系统可以从包括浏览会话的记录的交互记录获得的web资源中提取结构化和/或半结构化参数。 来自提取参数的内容可以使用本体来比较,以查找Web资源和查询资源之间的关系。

    Method and system for entity linking

    公开(公告)号:US10289957B2

    公开(公告)日:2019-05-14

    申请号:US14585315

    申请日:2014-12-30

    Applicant: Yahoo! Inc.

    Abstract: The present teaching relates to entity linking. In one example, a text string is received. The text string is segmented to obtain a segmentation with a set of one or more segments of the text string. A set of entities are identified, with respect to the one or more segments, from a plurality of entities as linked to the one or more segments. The identifying is in accordance with a probabilistic model based on surface form information associated with the plurality of entities.

    WEB CRAWLING
    5.
    发明申请
    WEB CRAWLING 审中-公开

    公开(公告)号:US20160125081A1

    公开(公告)日:2016-05-05

    申请号:US14530558

    申请日:2014-10-31

    Applicant: Yahoo! Inc.

    CPC classification number: G06F16/951 G06F16/353 G06F16/986

    Abstract: Briefly, embodiments disclosed herein may relate to Web crawling, and more particularly may relate to Web crawling for structured content, for example.

    Abstract translation: 简而言之,本文公开的实施例可以涉及Web爬行,并且更具体地可以涉及例如用于结构化内容的Web爬行。

    Entity disambiguation
    6.
    发明授权

    公开(公告)号:US11907858B2

    公开(公告)日:2024-02-20

    申请号:US15425978

    申请日:2017-02-06

    Applicant: Yahoo!, Inc.

    CPC classification number: G06N5/04 G06F16/36

    Abstract: One or more computing devices, systems, and/or methods for entity disambiguation are provided. For example, a document may be analyzed to identify a first mention and a second mention. One or more techniques may be used to select and link a candidate entity, from a first set of candidate entities, to the first mention and select and link a candidate entity, from a second set of candidate entities, to the second mention.

    ENTITY DISAMBIGUATION
    7.
    发明申请

    公开(公告)号:US20180225576A1

    公开(公告)日:2018-08-09

    申请号:US15425978

    申请日:2017-02-06

    Applicant: Yahoo!, Inc.

    CPC classification number: G06N5/04 G06F16/36

    Abstract: One or more computing devices, systems, and/or methods for entity disambiguation are provided. For example, a document may be analyzed to identify a first mention and a second mention. One or more techniques may be used to select and link a candidate entity, from a first set of candidate entities, to the first mention and select and link a candidate entity, from a second set of candidate entities, to the second mention.

Patent Agency Ranking