利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

29 条记录 (耗时 0.029 秒)

    EVIDENCE DIFFUSION AMONG CANDIDATE ANSWERS DURING QUESTION ANSWERING
    12.
    发明申请
    EVIDENCE DIFFUSION AMONG CANDIDATE ANSWERS DURING QUESTION ANSWERING 有权
    问题答复中的候选答复中的证据扩散

    公开(公告)号：US20130018652A1

    公开(公告)日：2013-01-17

    申请号：US13616924

    申请日：2012-09-14

    申请人： David A. Ferrucci ,  David C. Gondek ,  Aditya A. Kalyanpur ,  Adam P. Lally

    发明人： David A. Ferrucci ,  David C. Gondek ,  Aditya A. Kalyanpur ,  Adam P. Lally

    IPC分类号： G06F17/27

    CPC分类号： G06F17/30654 ,  G06F17/30507

    摘要： 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.

    摘要翻译： 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。

    Predicting lexical answer types in open domain question and answering (QA) systems
    13.
    发明授权
    Predicting lexical answer types in open domain question and answering (QA) systems 有权
    预测开放式问答环境（QA）系统中的词汇应答类型

    公开(公告)号：US09015031B2

    公开(公告)日：2015-04-21

    申请号：US13552260

    申请日：2012-07-18

    申请人： David A. Ferrucci ,  Alfio M. Gliozzo ,  Aditya A. Kalyanpur

    发明人： David A. Ferrucci ,  Alfio M. Gliozzo ,  Aditya A. Kalyanpur

    IPC分类号： G10L15/00 ,  G06F17/27 ,  G06F17/30

    CPC分类号： G06F17/2785 ,  G06F17/30976

    摘要： In an automated Question Answer (QA) system architecture for automatic open-domain Question Answering, a system, method and computer program product for predicting the Lexical Answer Type (LAT) of a question. The approach is completely unsupervised and is based on a large-scale lexical knowledge base automatically extracted from a Web corpus. This approach for predicting the LAT can be implemented as a specific subtask of a QA process, and/or used for general purpose knowledge acquisition tasks such as frame induction from text.

    摘要翻译： 在用于自动开放域问题回答的自动问题答案（QA）系统架构中，一种用于预测问题的词汇答案类型（LAT）的系统，方法和计算机程序产品。 该方法是完全无监督的，并且基于从Web语料库自动提取的大规模词汇知识库。 用于预测LAT的这种方法可以被实现为QA过程的特定子任务，和/或用于通用目的知识获取任务，例如来自文本的帧归纳。

    USING ONTOLOGICAL INFORMATION IN OPEN DOMAIN TYPE COERCION
    15.
    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：US20120330921A1

    公开(公告)日：2012-12-27

    申请号：US13605339

    申请日：2012-09-06

    申请人： David A. Ferrucci ,  Aditya A. Kalyanpur ,  James W. Murdock, IV ,  Christopher A. Welty ,  Wlodek W. Zadrozny

    发明人： David A. Ferrucci ,  Aditya A. Kalyanpur ,  James W. Murdock, IV ,  Christopher A. Welty ,  Wlodek W. Zadrozny

    IPC分类号： G06F17/30

    CPC分类号： G06N5/02 ,  G06F17/30654

    摘要： 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.

    摘要翻译： 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。

    PREDICTING LEXICAL ANSWER TYPES IN OPEN DOMAIN QUESTION AND ANSWERING (QA) SYSTEMS
    16.
    发明申请
    PREDICTING LEXICAL ANSWER TYPES IN OPEN DOMAIN QUESTION AND ANSWERING (QA) SYSTEMS 有权
    开放领域问题和答案（QA）系统中预测的解答类型

    公开(公告)号：US20130035931A1

    公开(公告)日：2013-02-07

    申请号：US13596636

    申请日：2012-08-28

    申请人： David A. Ferrucci ,  Alfio M. Gliozzo ,  Aditya A. Kalyanpur

    发明人： David A. Ferrucci ,  Alfio M. Gliozzo ,  Aditya A. Kalyanpur

    IPC分类号： G06F17/27

    CPC分类号： G06F17/2785 ,  G06F17/30976

    摘要： In an automated Question Answer (QA) system architecture for automatic open-domain Question Answering, a system, method and computer program product for predicting the Lexical Answer Type (LAT) of a question. The approach is completely unsupervised and is based on a large-scale lexical knowledge base automatically extracted from a Web corpus. This approach for predicting the LAT can be implemented as a specific subtask of a QA process, and/or used for general purpose knowledge acquisition tasks such as frame induction from text.

    摘要翻译： 在用于自动开放域问题回答的自动问题答案（QA）系统架构中，一种用于预测问题的词汇答案类型（LAT）的系统，方法和计算机程序产品。 该方法是完全无监督的，并且基于从Web语料库自动提取的大规模词汇知识库。 用于预测LAT的这种方法可以被实现为QA过程的特定子任务，和/或用于通用目的知识获取任务，例如来自文本的帧归纳。

    Predicting lexical answer types in open domain question and answering (QA) systems
    19.
    发明授权
    Predicting lexical answer types in open domain question and answering (QA) systems 有权
    预测开放式问答环境（QA）系统中的词汇应答类型

    公开(公告)号：US08880388B2

    公开(公告)日：2014-11-04

    申请号：US13596636

    申请日：2012-08-28

    申请人： David A. Ferrucci ,  Alfio M. Gliozzo ,  Aditya A. Kalyanpur

    发明人： David A. Ferrucci ,  Alfio M. Gliozzo ,  Aditya A. Kalyanpur

    IPC分类号： G10L15/00

    CPC分类号： G06F17/2785 ,  G06F17/30976

    摘要： In an automated Question Answer (QA) system architecture for automatic open-domain Question Answering, a system, method and computer program product for predicting the Lexical Answer Type (LAT) of a question. The approach is completely unsupervised and is based on a large-scale lexical knowledge base automatically extracted from a Web corpus. This approach for predicting the LAT can be implemented as a specific subtask of a QA process, and/or used for general purpose knowledge acquisition tasks such as frame induction from text.

    摘要翻译： 在用于自动开放域问题回答的自动问题答案（QA）系统架构中，一种用于预测问题的词汇答案类型（LAT）的系统，方法和计算机程序产品。 该方法是完全无监督的，并且是基于从Web语料库自动提取的大规模词汇知识库。 用于预测LAT的这种方法可以被实现为QA过程的特定子任务，和/或用于通用目的知识获取任务，例如来自文本的帧归纳。