中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

5 records (took 0.021 seconds)

    USING ONTOLOGICAL INFORMATION IN OPEN DOMAIN TYPE COERCION
    1.
    发明申请
    USING ONTOLOGICAL INFORMATION IN OPEN DOMAIN TYPE COERCION 审中-公开
    在开放类型的科学中使用本体信息

    公开(公告)号：WO2012040676A1

    公开(公告)日：2012-03-29

    申请号：PCT/US2011/053167

    申请日：2011-09-24

    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION ,  FERRUCCI, David A. ,  KALYANPUR, Aditya A. ,  MURDOCK IV, James W. ,  WELTY, Christopher A. ,  ZADROZNY, Wlodek W.

    Inventor： FERRUCCI, David A. ,  KALYANPUR, Aditya A. ,  MURDOCK IV, James W. ,  WELTY, Christopher A. ,  ZADROZNY, Wlodek W.

    IPC: G06F7/00 ,  G06F17/00

    CPC classification number: G06N5/02 ,  G06F17/30654

    Abstract: A computer-implemented system, method and program product generates answers to questions in an input query text string. The method includes determining, by a programmed processor unit, a lexical answer type (LAT) string associated with an input query; automatically obtaining a candidate answer string to the input query from a data corpus; mapping the query LAT string to a first type string in a structured resource; mapping the candidate answer string to a second type string in the structured resource; and determining if the first type string and the second type string are disjointed; and scoring the candidate answer string based on the determination of the types being disjointed wherein the structured resource includes a semantic database providing ontological content.

    Abstract translation: 计算机实现的系统，方法和程序产品会在输入查询文本字符串中生成问题的答案。 该方法包括由编程的处理器单元确定与输入查询相关联的词汇答案类型（LAT）字符串; 从数据语料库自动获得候选答案字符串到输入查询; 将查询LAT字符串映射到结构化资源中的第一个类型的字符串; 将候选答案字符串映射到结构化资源中的第二类型字符串; 以及确定所述第一类型字符串和所述第二类型字符串是否脱离; 以及基于所述不相交类型的确定对所述候选答案字符串进行评分，其中所述结构化资源包括提供本体内容的语义数据库。

    EVIDENCE DIFFUSION AMONG CANDIDATE ANSWERS DURING QUESTION ANSWERING
    2.
    发明申请
    EVIDENCE DIFFUSION AMONG CANDIDATE ANSWERS DURING QUESTION ANSWERING 审中-公开
    问题答复中的候选答复中的证据扩散

    公开(公告)号：WO2012047557A1

    公开(公告)日：2012-04-12

    申请号：PCT/US2011/053049

    申请日：2011-09-23

    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION ,  FERRUCCI, David, A. ,  GONDEK, David, C. ,  KALYANPUR, Aditya, A. ,  LALLY, Adam, P.

    Inventor： FERRUCCI, David, A. ,  GONDEK, David, C. ,  KALYANPUR, Aditya, A. ,  LALLY, Adam, P.

    IPC: G10L15/18

    CPC classification number: G06F17/30654 ,  G06F17/30507

    Abstract: Diffusing evidence among candidate answers during question answering may identify a relationship between a first candidate answer and a second candidate answer, wherein the candidate answers are generated by a question-answering computer process, the candidate answers have associated supporting evidence, and the candidate answers have associated confidence scores. All or some of the evidence may be transferred from the first candidate answer to the second candidate answer based on the identified relationship. A new confidence score may be computed for the second candidate answer based on the transferred evidence.

    Abstract translation: 在问题回答期间候选答案之间的扩散证据可以识别第一候选答案和第二候选答案之间的关系，其中候选答案由问答电脑程序产生，候选答案具有相关的支持证据，候选答案具有 相关的信心分数。 基于所识别的关系，所有或一些证据可以从第一候选答案转移到第二候选答案。 可以基于转移的证据为第二候选答案计算新的置信度。

    MULTI-DIMENSIONAL FEATURE MERGING FOR OPEN DOMAIN QUESTION ANSWERING
    3.
    发明申请
    MULTI-DIMENSIONAL FEATURE MERGING FOR OPEN DOMAIN QUESTION ANSWERING 审中-公开
    多维特征合并开放领域问题解答

    公开(公告)号：WO2014078612A3

    公开(公告)日：2014-09-12

    申请号：PCT/US2013070219

    申请日：2013-11-15

    Applicant: IBM ,  AGARWAL APOORV ,  CHU-CARROLL JENNIFER ,  KALYANPUR ADITYA A ,  LALLY ADAM P ,  MURDOCK JAMES W ,  TOMEK LORRIE A

    Inventor： AGARWAL APOORV ,  CHU-CARROLL JENNIFER ,  KALYANPUR ADITYA A ,  LALLY ADAM P ,  MURDOCK JAMES W ,  TOMEK LORRIE A

    IPC: G06N5/02 ,  G09B7/00 ,  G09B19/00

    CPC classification number: G09B7/00 ,  G06N5/02 ,  G09B7/04 ,  G09B19/00

    Abstract: Methods/systems receive a question and automatically search sources of data containing passages to produce candidate answers to the question. The searching identifies passages that support each of the candidate answers based on scoring features that indicate whether the candidate answers are correct answers to the question. These methods/systems automatically create a scoring feature- specific matrix for each scoring feature. Each scoring feature-specific matrix has a score field for each different combination of text passage and question term (vector), and each score field holds a score value (vector value) indicating how each different combination of text passage and question term supports the candidate answers as being a correct answer to the question. Next, such methods/systems automatically combine multiple such vectors to produce a combined vector score for each of the candidate answers, and then rank the candidate answers based on the combined scores.

    Abstract translation: 方法/系统收到一个问题，并自动搜索包含段落的数据源，以产生候选题回答。 该搜索基于评分特征来识别支持每个候选答案的段落，所述评分特征指示候选答案是否是问题的正确答案。 这些方法/系统为每个评分特征自动创建一个评分特征专用矩阵。 每个得分特征专用矩阵对于文本通过和问题项（向量）的每个不同组合具有得分字段，并且每个得分字段保持指示文本通过和问题项的每个不同组合如何支持候选者的得分值（向量值） 答案是对这个问题的正确答案。 接下来，这些方法/系统自动组合多个这样的向量以产生每个候选答案的组合向量分数，然后基于组合分数对候选答案进行排序。

    MULTI-DIMENSIONAL FEATURE MERGING FOR OPEN DOMAIN QUESTION ANSWERING
    4.
    发明申请
    MULTI-DIMENSIONAL FEATURE MERGING FOR OPEN DOMAIN QUESTION ANSWERING 审中-公开
    用于开放领域问题的多维特征兼并

    公开(公告)号：WO2014078612A2

    公开(公告)日：2014-05-22

    申请号：PCT/US2013/070219

    申请日：2013-11-15

    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION ,  AGARWAL, Apoorv ,  CHU-CARROLL, Jennifer ,  KALYANPUR, Aditya, A. ,  LALLY, Adam, P. ,  MURDOCK, James, W., ,  TOMEK, Lorrie, A.

    Inventor： AGARWAL, Apoorv ,  CHU-CARROLL, Jennifer ,  KALYANPUR, Aditya, A. ,  LALLY, Adam, P. ,  MURDOCK, James, W., ,  TOMEK, Lorrie, A.

    IPC: G06F17/30

    CPC classification number: G09B7/00 ,  G06N5/02 ,  G09B7/04 ,  G09B19/00

    Abstract: Methods/systems receive a question and automatically search sources of data containing passages to produce candidate answers to the question. The searching identifies passages that support each of the candidate answers based on scoring features that indicate whether the candidate answers are correct answers to the question. These methods/systems automatically create a scoring feature- specific matrix for each scoring feature. Each scoring feature-specific matrix has a score field for each different combination of text passage and question term (vector), and each score field holds a score value (vector value) indicating how each different combination of text passage and question term supports the candidate answers as being a correct answer to the question. Next, such methods/systems automatically combine multiple such vectors to produce a combined vector score for each of the candidate answers, and then rank the candidate answers based on the combined scores.

    Abstract translation: 方法/系统会收到一个问题，并自动搜索包含段落的数据源，以产生问题的候选答案。 搜索根据评分特征来识别支持每个候选答案的段落，该特征指示候选答案是否是该问题的正确答案。 这些方法/系统会自动为每个评分功能创建一个评分特征矩阵。 每个得分特征矩阵具有文本通过和问题项（向量）的每个不同组合的得分字段，并且每个得分字段保存指示文本通过和问题项的每个不同组合如何支持候选者的分数值（向量值） 答案是对问题的正确答案。 接下来，这样的方法/系统自动组合多个这样的向量以产生每个候选答案的组合向量得分，然后基于组合得分来排列候选答案。

Patent Agency Ranking