System and Method of Semi-Supervised Learning for Spoken Language Understanding Using Semantic Role Labeling
    1.
    发明申请
    System and Method of Semi-Supervised Learning for Spoken Language Understanding Using Semantic Role Labeling 有权
    使用语义角色标签的语言认知的半监督学习的系统和方法

    公开(公告)号:US20130085756A1

    公开(公告)日:2013-04-04

    申请号:US13684939

    申请日:2012-11-26

    申请人: AT&T Corp.

    IPC分类号: G10L15/06

    CPC分类号: G10L15/063 G09B19/04

    摘要: A system and method are disclosed for providing semi-supervised learning for a spoken language understanding module using semantic role labeling. The method embodiment relates to a method of generating a spoken language understanding module. Steps in the method comprise selecting at least one predicate/argument pair as an intent from a set of the most frequent predicate/argument pairs for a domain, labeling training data using mapping rules associated with the selected at least one predicate/argument pair, training a call-type classification model using the labeled training data, re-labeling the training data using the call-type classification model and iteratively several of the above steps until training set labels converge.

    摘要翻译: 公开了一种用于为使用语义角色标记的口语理解模块提供半监督学习的系统和方法。 该方法实施例涉及一种产生口头语言理解模块的方法。 方法中的步骤包括从一个域的最频繁谓词/参数对集合中选择至少一个谓词/参数对作为意图,使用与所选择的至少一个谓词/参数对相关联的映射规则来标记训练数据,训练 使用标记的训练数据的呼叫类型分类模型,使用呼叫类型分类模型重新标记训练数据,并且迭代地执行上述几个步骤,直到训练集标签收敛。

    System and method of semi-supervised learning for spoken language understanding using semantic role labeling
    2.
    发明授权
    System and method of semi-supervised learning for spoken language understanding using semantic role labeling 有权
    使用语义角色标签进行口语理解的半监督学习的系统和方法

    公开(公告)号:US08548805B2

    公开(公告)日:2013-10-01

    申请号:US13684939

    申请日:2012-11-26

    申请人: AT&T Corp.

    IPC分类号: G10L15/06

    CPC分类号: G10L15/063 G09B19/04

    摘要: A system and method are disclosed for providing semi-supervised learning for a spoken language understanding module using semantic role labeling. The method embodiment relates to a method of generating a spoken language understanding module. Steps in the method comprise selecting at least one predicate/argument pair as an intent from a set of the most frequent predicate/argument pairs for a domain, labeling training data using mapping rules associated with the selected at least one predicate/argument pair, training a call-type classification model using the labeled training data, re-labeling the training data using the call-type classification model and iteratively several of the above steps until training set labels converge.

    摘要翻译: 公开了一种用于为使用语义角色标记的口语理解模块提供半监督学习的系统和方法。 该方法实施例涉及一种产生口头语言理解模块的方法。 该方法中的步骤包括从一个域的最频繁谓词/参数对集合中选择至少一个谓词/参数对作为意图,使用与所选择的至少一个谓词/参数对相关联的映射规则来标记训练数据,训练 使用标记的训练数据的呼叫类型分类模型,使用呼叫类型分类模型重新标记训练数据,并且迭代地执行上述几个步骤,直到训练集标签收敛。