Customization of a Natural Language Processing Engine
    1.
    发明申请
    Customization of a Natural Language Processing Engine 有权
    自然语言处理引擎的定制

    公开(公告)号:US20130030792A1

    公开(公告)日:2013-01-31

    申请号:US13190962

    申请日:2011-07-26

    IPC分类号: G06F17/27

    CPC分类号: G06F17/2818 G06F17/2872

    摘要: A method, an apparatus and an article of manufacture for customizing a natural language processing engine. The method includes enabling selection of one or more parameters of a desired natural language processing task, the one or more parameters intended for use by a trained and an untrained user, mapping the one or more selected parameters to a collection of one or more intervals of an input parameter to an optimization algorithm, and applying the optimization algorithm with the collection of one or more intervals of an input parameter to a model used by a natural language processing engine to produce a customized model.

    摘要翻译: 一种用于定制自然语言处理引擎的方法,装置和制品。 该方法包括使得能够选择期望的自然语言处理任务的一个或多个参数,所述一个或多个参数旨在由受过训练和未经训练的用户使用,将一个或多个所选择的参数映射到一个或多个间隔的集合 对优化算法的输入参数,以及将优化算法与输入参数的一个或多个间隔的集合应用于由自然语言处理引擎使用的模型以产生定制模型。

    Predicting pronouns of dropped pronoun style languages for natural language translation
    2.
    发明授权
    Predicting pronouns of dropped pronoun style languages for natural language translation 有权
    预测用于自然语言翻译的代词缩略语言代词

    公开(公告)号:US08903707B2

    公开(公告)日:2014-12-02

    申请号:US13348995

    申请日:2012-01-12

    IPC分类号: G06F17/28

    CPC分类号: G06F17/2827

    摘要: A method, an apparatus and an article of manufacture for determining a dropped pronoun from a source language. The method includes collecting parallel sentences from a source and a target language, creating at least one word alignment between the parallel sentences in the source and the target language, mapping at least one pronoun from the target language sentence onto the source language sentence, computing at least one feature from the mapping, wherein the at least one feature is extracted from both the source language and the at least one pronoun projected from the target language, and using the at least one feature to train a classifier to predict position and spelling of at least one pronoun in the target language when the at least one pronoun is dropped in the source language.

    摘要翻译: 一种用于从源语言确定掉落代词的方法,装置和制品。 该方法包括从源和目标语言收集并行句子,在源和目标语言中的并行句子之间创建至少一个单词对齐,将来自目标语言句子的至少一个代词映射到源语言句子上,计算 所述映射中的至少一个特征,其中从所述源语言和从所述目标语言投射的所述至少一个代词中提取所述至少一个特征,并且使用所述至少一个特征来训练分类器来预测位置和拼写的位置和拼写 当至少一个代词在源语言中被删除时,目标语言中至少有一个代词。

    Customization of a natural language processing engine
    3.
    发明授权
    Customization of a natural language processing engine 有权
    自定义语言处理引擎

    公开(公告)号:US08725496B2

    公开(公告)日:2014-05-13

    申请号:US13190962

    申请日:2011-07-26

    IPC分类号: G06F17/27 G10L15/00

    CPC分类号: G06F17/2818 G06F17/2872

    摘要: A method, an apparatus and an article of manufacture for customizing a natural language processing engine. The method includes enabling selection of one or more parameters of a desired natural language processing task, the one or more parameters intended for use by a trained and an untrained user, mapping the one or more selected parameters to a collection of one or more intervals of an input parameter to an optimization algorithm, and applying the optimization algorithm with the collection of one or more intervals of an input parameter to a model used by a natural language processing engine to produce a customized model.

    摘要翻译: 一种用于定制自然语言处理引擎的方法,装置和制品。 该方法包括使得能够选择期望的自然语言处理任务的一个或多个参数,所述一个或多个参数旨在由受过训练和未经训练的用户使用,将一个或多个所选择的参数映射到一个或多个间隔的集合 对优化算法的输入参数,以及将优化算法与输入参数的一个或多个间隔的集合应用于由自然语言处理引擎使用的模型以产生定制模型。

    Optimization of natural language processing system based on conditional output quality at risk
    4.
    发明授权
    Optimization of natural language processing system based on conditional output quality at risk 有权
    基于条件输出质量风险的自然语言处理系统优化

    公开(公告)号:US08660836B2

    公开(公告)日:2014-02-25

    申请号:US13073255

    申请日:2011-03-28

    IPC分类号: G10L15/00

    CPC分类号: G06F17/2818 G06F17/2854

    摘要: Techniques are disclosed for optimizing results output by a natural language processing system. For example, a method comprises optimizing one or more parameters of a natural language processing system so as to improve a measure of quality of an output of the natural language processing system for a first type of data processed by the natural language processing system while maintaining a given measure of quality of an output of the natural language processing system for a second type of data processed by the natural language processing system. For example, the first type of data may have a substantive complexity that is greater than that of the second type of data. Thus, when the natural language processing system is a machine translation system, use of a conditional value at risk metric for the translation quality provides for a high quality output of the machine translation system for data of a high substantive complexity (for sophisticated users) while maintaining an average quality output for average data (for average users).

    摘要翻译: 公开了用于优化由自然语言处理系统输出的结果的技术。 例如,一种方法包括优化自然语言处理系统的一个或多个参数,以便改善对于由自然语言处理系统处理的第一类型的数据的自然语言处理系统的输出的质量的量度,同时保持 给出自然语言处理系统对自然语言处理系统处理的第二类数据的输出质量的度量。 例如,第一类型的数据可能具有大于第二类型的数据的实质性复杂度。 因此,当自然语言处理系统是机器翻译系统时,使用翻译质量的风险度量条件值为机器翻译系统提供高质量的高实质性复杂性(针对复杂用户)的数据输出,同时 维持平均数据(平均用户)的平均质量输出。

    Predicting Pronouns for Pro-Drop Style Languages for Natural Language Translation
    5.
    发明申请
    Predicting Pronouns for Pro-Drop Style Languages for Natural Language Translation 有权
    预测自然语言翻译中Pro-Drop风格语言的代词

    公开(公告)号:US20130185049A1

    公开(公告)日:2013-07-18

    申请号:US13348995

    申请日:2012-01-12

    IPC分类号: G06F17/28 G06F17/27

    CPC分类号: G06F17/2827

    摘要: A method, an apparatus and an article of manufacture for determining a dropped pronoun from a source language. The method includes collecting parallel sentences from a source and a target language, creating at least one word alignment between the parallel sentences in the source and the target language, mapping at least one pronoun from the target language sentence onto the source language sentence, computing at least one feature from the mapping, wherein the at least one feature is extracted from both the source language and the at least one pronoun projected from the target language, and using the at least one feature to train a classifier to predict position and spelling of at least one pronoun in the target language when the at least one pronoun is dropped in the source language.

    摘要翻译: 一种用于从源语言确定掉落代词的方法,装置和制品。 该方法包括从源和目标语言收集并行句子,在源和目标语言中的并行句子之间创建至少一个单词对齐,将来自目标语言句子的至少一个代词映射到源语言句子上,计算 所述映射中的至少一个特征,其中从所述源语言和从所述目标语言投射的所述至少一个代词中提取所述至少一个特征,并且使用所述至少一个特征来训练分类器来预测位置和拼写的位置和拼写 当至少一个代词在源语言中被删除时,目标语言中至少有一个代词。

    OPTIMIZATION OF NATURAL LANGUAGE PROCESSING SYSTEM BASED ON CONDITIONAL OUTPUT QUALITY AT RISK
    6.
    发明申请
    OPTIMIZATION OF NATURAL LANGUAGE PROCESSING SYSTEM BASED ON CONDITIONAL OUTPUT QUALITY AT RISK 有权
    基于条件输出质量风险的自然语言处理系统优化

    公开(公告)号:US20120253783A1

    公开(公告)日:2012-10-04

    申请号:US13073255

    申请日:2011-03-28

    IPC分类号: G06F17/28 G06F17/27

    CPC分类号: G06F17/2818 G06F17/2854

    摘要: Techniques are disclosed for optimizing results output by a natural language processing system. For example, a method comprises optimizing one or more parameters of a natural language processing system so as to improve a measure of quality of an output of the natural language processing system for a first type of data processed by the natural language processing system while maintaining a given measure of quality of an output of the natural language processing system for a second type of data processed by the natural language processing system. For example, the first type of data may have a substantive complexity that is greater than that of the second type of data. Thus, when the natural language processing system is a machine translation system, use of a conditional value at risk metric for the translation quality provides for a high quality output of the machine translation system for data of a high substantive complexity (for sophisticated users) while maintaining an average quality output for average data (for average users).

    摘要翻译: 公开了用于优化由自然语言处理系统输出的结果的技术。 例如,一种方法包括优化自然语言处理系统的一个或多个参数,以便改善对于由自然语言处理系统处理的第一类型的数据的自然语言处理系统的输出的质量的量度,同时保持 给出自然语言处理系统对自然语言处理系统处理的第二类数据的输出质量的度量。 例如,第一类型的数据可能具有大于第二类型的数据的实质性复杂度。 因此,当自然语言处理系统是机器翻译系统时,使用翻译质量的风险度量条件值为机器翻译系统提供高质量的高实质性复杂性(针对复杂用户)的数据输出,同时 维持平均数据(平均用户)的平均质量输出。

    Remote GUI control by replication of local interactions
    8.
    发明授权
    Remote GUI control by replication of local interactions 有权
    通过复制本地交互来远程GUI控制

    公开(公告)号:US08640034B2

    公开(公告)日:2014-01-28

    申请号:US11560384

    申请日:2006-11-16

    IPC分类号: G06F3/00

    摘要: Under the present invention, an illustrative feature is to provide a method and system/structure for remotely controlling multiple computer systems by interacting with GUIs. Specifically, the present invention allows a controlled computer/system to be remotely controlled via a controlling computer/system. To this extent, data/action capture instrumentation is provided on the controlling system for automatically creating a representation of content of the GUI of the controlling system, for automatically observing a set of actions performed by a user on the GUI of the controlling system, for automatically creating a representation of the observed actions, and for sending to the controlled system the representation of the observed actions. In addition, execution instrumentation is provided on the controlled system for receiving the representation and replicating the actions on the controlled system by interacting with a GUI of the controlled system.

    摘要翻译: 在本发明中,说明性的特征是提供一种用于通过与GUI交互来远程控制多个计算机系统的方法和系统/结构。 具体地,本发明允许受控计算机/系统通过控制计算机/系统进行远程控制。 在这种程度上,在控制系统上提供数据/动作捕获仪器,用于自动创建控制系统的GUI的内容的表示,用于自动观察由用户在控制系统的GUI上执行的一组动作,用于 自动创建观察到的动作的表示,以及向受控系统发送观察到的动作的表示。 此外,在受控系统上提供执行仪器,用于通过与受控系统的GUI交互来接收表示和复制受控系统上的动作。

    System and Method for Automatically Detecting and Interactively Displaying Information About Entities, Activities, and Events from Multiple-Modality Natural Language Sources
    9.
    发明申请
    System and Method for Automatically Detecting and Interactively Displaying Information About Entities, Activities, and Events from Multiple-Modality Natural Language Sources 审中-公开
    自动检测和交互式显示多模式自然语言源的实体,活动和事件信息的系统和方法

    公开(公告)号:US20130332450A1

    公开(公告)日:2013-12-12

    申请号:US13493659

    申请日:2012-06-11

    IPC分类号: G06F17/30 G06F17/28

    摘要: A method for automatically extracting and organizing information by a processing device from a plurality of data sources is provided. A natural language processing information extraction pipeline that includes an automatic detection of entities is applied to the data sources. Information about detected entities is identified by analyzing products of the natural language processing pipeline. Identified information is grouped into equivalence classes containing equivalent information. At least one displayable representation of the equivalence classes is created. An order in which the at least one displayable representation is displayed is computed. A combined representation of the equivalence classes that respects the order in which the displayable representation is displayed is produced.

    摘要翻译: 提供了一种通过处理装置从多个数据源自动提取和组织信息的方法。 包括实体的自动检测的自然语言处理信息提取流水线被应用于数据源。 通过分析自然语言处理流水线的产品来识别检测到的实体信息。 识别的信息被分为包含等效信息的等价类。 创建等价类的至少一个可显示的表示形式。 计算显示至少一个可显示表示的顺序。 产生了相当于显示可显示表示的顺序的等价类的组合表示。