利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

40 条记录 (耗时 0.028 秒)

    Systems and methods for language feature generation over multi-layered word representation
    21.
    发明授权
    Systems and methods for language feature generation over multi-layered word representation 有权

    公开(公告)号：US10073834B2

    公开(公告)日：2018-09-11

    申请号：US15018877

    申请日：2016-02-09

    申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

    发明人： Ran Levy ,  Eyal Shnarch ,  Noam Slonim

    IPC分类号： G06F17/27 ,  G06F17/30

    CPC分类号： G06F17/278 ,  G06F16/353 ,  G06F16/36 ,  G06F17/2715 ,  G06F17/2785

    摘要： There is provided a computer-implemented method for outputting one or more cross-layer patterns to identify a target semantic phenomenon in text, the method comprising: extracting, for each word of at least some words of each training text fragment of training text fragments designated as representing a target semantic phenomenon, feature-values defined by respective layers; statistically analyzing the feature-values identified for the training text fragments to identify one or more cross-layer patterns comprising layers representing a common pattern for the training text fragments, the common cross-layer pattern defining one or more feature-values of a respective layer of one or more words and at least another feature-value of another respective layer of another word; and outputting the identified cross-layer pattern(s) for identifying a text fragment representing the target semantic phenomenon.

    CLAIM GENERATION
    23.
    发明申请
    CLAIM GENERATION 审中-公开

    公开(公告)号：US20180012127A1

    公开(公告)日：2018-01-11

    申请号：US15206326

    申请日：2016-07-11

    申请人： International Business Machines Corporation

    发明人： YONATAN BILU ,  Ran Levy ,  Noam Slonim

    IPC分类号： G06N5/02 ,  G06N99/00

    摘要： A computer-implemented method, computerized apparatus and computer program product for claim generation, the method comprising: selecting at least one subject according to a given topic; selecting at least one verb from a first data source; selecting at least one object from a second data source; generating one or more candidate claim sentences, each of which composed of a subject selected from the at least one subject, a verb selected from the at least one verb and an object selected from the at least on object; and determining validity of the candidate claim sentences using a machine learning process.

    Classification reliability prediction
    25.
    发明授权
    Classification reliability prediction 有权
    分类可靠性预测

    公开(公告)号：US09342789B2

    公开(公告)日：2016-05-17

    申请号：US14729080

    申请日：2015-06-03

    申请人： International Business Machines Corporation

    发明人： Ehud Aharoni ,  Ruty Rinott ,  Noam Slonim

    IPC分类号： G06F15/18 ,  G06N5/04 ,  G06Q10/10 ,  G06Q50/24 ,  G06N99/00 ,  G06F17/30 ,  G06K9/62

    CPC分类号： G06N5/048 ,  G06F17/30705 ,  G06F19/00 ,  G06K9/6265 ,  G06N99/005 ,  G06Q10/10 ,  G06Q50/24

    摘要： A method, apparatus and product useful for classification reliability prediction. The method being a computer-implemented method performed by a processor, the method comprising: obtaining a prediction of a label for a dataset made by a classifier tool, wherein the classifier tool is aimed at predicting the label based on a classification model and in view of a set of features defining the dataset; obtaining a reliability prediction of a reliability label relating to the prediction of the classifier tool based on a reliability classifier tool, wherein the reliability classifier tool is aimed at predicting the reliability label based on a classification model and in view of a second set of features; and outputting to a user the label prediction and an associated reliability prediction.

    摘要翻译： 一种用于分类可靠性预测的方法，装置和产品。 该方法是由处理器执行的由计算机实现的方法，所述方法包括：获得由分类器工具制作的数据集的标签的预测，其中所述分类器工具旨在基于分类模型和视图来预测所述标签 定义数据集的一组特征; 基于可靠性分类器工具获得与所述分类器工具的预测相关的可靠性标签的可靠性预测，其中所述可靠性分类器工具旨在基于分类模型和第二组特征来预测所述可靠性标签; 并向用户输出标签预测和相关的可靠性预测。

    DISAMBIGUATION IN MENTION DETECTION
    26.
    发明申请
    DISAMBIGUATION IN MENTION DETECTION 审中-公开
    禁止检测

    公开(公告)号：US20160124939A1

    公开(公告)日：2016-05-05

    申请号：US14926260

    申请日：2015-10-29

    申请人： International Business Machines Corporation

    发明人： Feng Cao ,  Yuan Ni ,  Noam Slonim ,  Qiongkai Xu ,  Hui Jia Zhu

    IPC分类号： G06F17/27 ,  G06F17/22

    CPC分类号： G06F17/278

    摘要： Disambiguation in mention detection. The method includes: determining at least one location in a text at which a target surface form in the text appears; obtaining an overall word-bag context of the target surface form in the text, the word-bag context at each of the at least one location including words within a predetermined neighborhood of the location; obtaining an overall resource context of the target surface form in the text, the resource context at each of the at least one location including resources corresponding to a further surface form within a predetermined neighborhood of the location; and determining a similarity between the target surface form and a candidate resource for the target surface form based on the overall word-bag context and the overall resource context. A system for disambiguation in mention detection is also provided.

    摘要翻译： 消除歧义提及检测。 该方法包括：确定出现文本中的目标表面形式的文本中的至少一个位置; 获取所述文本中的目标表面形式的整体文字袋上下文，所述至少一个位置中的每个位置处的所述单词包上下文包括所述位置的预定邻域内的单词; 获取所述文本中的目标表面形式的总体资源上下文，所述至少一个位置中的每一个处的资源上下文包括与所述位置的预定邻域内的另一表面形式相对应的资源; 以及基于所述整体文字包上下文和所述整体资源上下文来确定所述目标表面形式与所述目标表面形式的候选资源之间的相似性。 还提供了一种消除歧义的系统来提及检测。

    AUTOMATIC CONSTRUCTION OF ARGUMENTS
    27.
    发明申请
    AUTOMATIC CONSTRUCTION OF ARGUMENTS 审中-公开
    自动构造的参数

    公开(公告)号：US20150317560A1

    公开(公告)日：2015-11-05

    申请号：US14265408

    申请日：2014-04-30

    申请人： International Business Machines Corporation

    发明人： Ehud Aharoni ,  Dan Gutfreund ,  Daniel Hershcovich ,  Tamar Lavee ,  Ran Levy ,  Ruty Rinott ,  Noam Slonim

    IPC分类号： G06N5/04 ,  G06N99/00

    CPC分类号： G06N5/04 ,  G06N20/00

    摘要： A method comprising using at least one hardware processor for receiving a topic under consideration (TUC); providing the TUC as input to a claim function, wherein the claim function is configured to mine at least one content resource, and applying the claim function to the at least one content resource, to extract claims with respect to the TUC; and providing the TUC as input to a classification function, and applying the classification function to one or more claims of the extracted claims, to output corresponding one or more classification tags, wherein each classification tag is associated with its corresponding claim.

    摘要翻译： 一种方法，包括使用至少一个硬件处理器来接收所考虑的主题（TUC）; 将所述TUC提供给权利要求功能的输入，其中所述权利要求功能被配置为挖掘至少一个内容资源，并且将所述权利要求功能应用于所述至少一个内容资源，以提取关于所述TUC的权利要求; 以及将所述TUC提供给分类功能的输入，以及将所述分类功能应用于所提取的权利要求的一个或多个权利要求，以输出相应的一个或多个分类标签，其中每个分类标签与其对应的权利要求相关联。

    AUTOMATED DETECTION OF REASONING IN ARGUMENTS
    28.
    发明公开
    AUTOMATED DETECTION OF REASONING IN ARGUMENTS 审中-公开

    公开(公告)号：US20240256779A1

    公开(公告)日：2024-08-01

    申请号：US18102721

    申请日：2023-01-29

    申请人： International Business Machines Corporation

    发明人： Avishai Gretz ,  Assaf Toledo ,  Edo Cohen-Karlik ,  Noam Slonim

    IPC分类号： G06F40/30 ,  G06F40/284

    CPC分类号： G06F40/30 ,  G06F40/284

    摘要： Automated detection of reasoning in arguments. A training set is generated by: obtaining multiple arguments, each comprising one or more sentences provided as digital text; automatically estimating a probability that each of the arguments includes reasoning, wherein the estimating comprises applying a contextual language model to each of the arguments; automatically labeling as positive examples those of the arguments which have a relatively high probability to include reasoning; and automatically labeling as negative examples those of the arguments which have a relatively low probability to include reasoning. Based on the generated training set, a machine learning classifier is automatically trained to estimate a probability that a new argument includes reasoning. The trained machine learning classifier is applied to the new argument, to estimate a probability that the new argument includes reasoning.