-
1.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
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。
-
2.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
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。
-
公开(公告)号：US20130035930A1
公开(公告)日：2013-02-07
申请号：US13552260
申请日：2012-07-18
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.
-
4.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
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。
-
公开(公告)号：US08738365B2
公开(公告)日：2014-05-27
申请号：US13616924
申请日：2012-09-14
IPC分类号： G06F17/30
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。
-
6.发明申请公开(公告)号：US20140072948A1
公开(公告)日：2014-03-13
申请号：US13610355
申请日：2012-09-11
申请人： Branimir K. Boguraev , David W. Buchanan , Jennifer Chu-Carroll , David A. Ferrucci , Aditya A. Kalyanpur , James W. Murdock, IV , Siddharth A. Patwardhan
发明人： Branimir K. Boguraev , David W. Buchanan , Jennifer Chu-Carroll , David A. Ferrucci , Aditya A. Kalyanpur , James W. Murdock, IV , Siddharth A. Patwardhan
IPC分类号： G09B7/00
CPC分类号： G09B7/00
摘要： A method of generating secondary questions in a question-answer system. Missing information is identified from a corpus of data using a computerized device. The missing information comprises any information that improves confidence scores for candidate answers to a question. The computerized device automatically generates a plurality of hypotheses concerning the missing information. The computerized device automatically generates at least one secondary question based on each of the plurality of hypotheses. The hypotheses are ranked based on relative utility to determine an order in which the computerized device outputs the at least one secondary question to external sources to obtain responses.
摘要翻译： 在问答系统中产生次要问题的方法。 使用计算机化设备从数据库中识别丢失的信息。 缺少的信息包括任何提高问题候选人答案的置信度分数的信息。 计算机化设备自动生成关于缺失信息的多个假设。 计算机化设备基于多个假设中的每一个自动生成至少一个次要问题。 基于相对效用对假设进行排序，以确定计算机化设备将至少一个次要问题输出到外部源以获得响应的顺序。
-
公开(公告)号：US20120323906A1
公开(公告)日：2012-12-20
申请号：US13597795
申请日：2012-08-29
申请人： James J. Fan , David A. Ferrucci , David C. Gondek , Aditya A. Kalyanpur , Adam P. Lally , James W. Murdock , Wlodek W. Zadrozny
发明人： James J. Fan , David A. Ferrucci , David C. Gondek , Aditya A. Kalyanpur , Adam P. Lally , James W. Murdock , Wlodek W. Zadrozny
IPC分类号： G06F17/30
CPC分类号： G09B7/00
摘要： A system, method and computer program product for automatically estimating the confidence of a detected LAT to provide a more accurate overall score for an obtained candidate answer. A confidence “score” or value of each detected LAT is obtained, and the system and method performs combining the confidence score with a degree of match between a LAT and an AnswerType of the candidate answer to provide improved overall score for the candidate answer.
摘要翻译： 一种用于自动估计检测到的LAT的置信度以为所获得的候选答案提供更准确的总分的系统，方法和计算机程序产品。 获得每个检测到的LAT的置信度分数或值，并且系统和方法执行将置信度分数与候选答案的LAT和答题类型之间的匹配度组合，以提供候选答案的改进的总分。
-
公开(公告)号：US20120078826A1
公开(公告)日：2012-03-29
申请号：US13247527
申请日：2011-09-28
申请人： David A. Ferrucci , David C. Gondek , Aditya A. Kalyanpur , Adam P. Lally , Siddharth Patwardham
发明人： David A. Ferrucci , David C. Gondek , Aditya A. Kalyanpur , Adam P. Lally , Siddharth Patwardham
CPC分类号： G06N7/005
摘要： A system, a method and a computer program product for verifying a statement are provided. The system is configured to receive a statement. The system is configured to decompose the received statement into one or more sets of question and answer pairs. The system is configured to determine a confidence value of each answer in the one or more question and answer pair sets. The system is configured to combine the determined confidence values. The combined confidence values represent a probability that the received statement is evaluated as true.
摘要翻译： 提供了一种用于验证语句的系统，方法和计算机程序产品。 系统配置为接收语句。 该系统被配置为将接收到的语句分解成一组或多组问答对。 该系统被配置为确定一个或多个问答对集合中每个答案的置信度值。 该系统被配置为组合确定的置信度值。 组合的置信度值表示接收到的语句被评估为真的概率。
-
公开(公告)号：US08972321B2
公开(公告)日：2015-03-03
申请号：US13247527
申请日：2011-09-28
申请人： David A. Ferrucci , David C. Gondek , Aditya A. Kalyanpur , Adam P. Lally , Siddharth Patwardham
发明人： David A. Ferrucci , David C. Gondek , Aditya A. Kalyanpur , Adam P. Lally , Siddharth Patwardham
CPC分类号： G06N7/005
摘要： A system, a method and a computer program product for verifying a statement are provided. The system is configured to receive a statement. The system is configured to decompose the received statement into one or more sets of question and answer pairs. The system is configured to determine a confidence value of each answer in the one or more question and answer pair sets. The system is configured to combine the determined confidence values. The combined confidence values represent a probability that the received statement is evaluated as true.
摘要翻译： 提供了一种用于验证语句的系统，方法和计算机程序产品。 系统配置为接收语句。 该系统被配置为将接收到的语句分解成一组或多组问答对。 该系统被配置为确定一个或多个问答对集合中每个答案的置信度值。 该系统被配置为组合确定的置信度值。 组合的置信度值表示接收到的语句被评估为真的概率。
-
公开(公告)号：US08738362B2
公开(公告)日：2014-05-27
申请号：US13243805
申请日：2011-09-23
IPC分类号： G06F17/30
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.
-
-
-
-
-
-
-
-
-
搜索结果
79 条记录 (耗时 0.036 秒)
