-
公开(公告)号：US10331684B2
公开(公告)日：2019-06-25
申请号：US15172216
申请日：2016-06-03
IPC分类号： G06F16/248 , G06F16/2457 , G06F16/28 , G06F16/33 , G06F16/34
摘要： Mechanisms are provided for implementing a candidate answer variant engine. The mechanisms receive an indication of a structured portion of content in a corpus, generate a plurality of groupings of elements of the structured portion of content, and generate, for each grouping of elements in the plurality of groupings of elements, and for each element in the grouping of elements, a corresponding grouping vector representation, corresponding to the element. The mechanisms, for each grouping vector representation of each grouping of elements in the plurality of groupings of elements perform a similarity measure calculation between the grouping vector representation and a vector representation of an input question, and select an element corresponding to the grouping vector representation for inclusion as a candidate answer variant based on results of the similarity measure calculation. The mechanisms perform question answering operations based on an analysis of one or more candidate answer variants.
-
公开(公告)号：US10242092B2
公开(公告)日：2019-03-26
申请号：US15794282
申请日：2017-10-26
发明人： Donna K. Byron , Devendra Goyal , Lakshminarayanan Krishnamurthy , Priscilla Santos Moraes , Michael C. Smith
摘要： Electronic natural language processing in a natural language processing (NLP) system, such as a Question-Answering (QA) system. A receives electronic text input, in question form, and determines a readability level indicator in the question. The readability level indicator includes at least a grammatical error, a slang term, and a misspelling type. The computer determines a readability level for the electronic text input based on the readability level indicator, and retrieves candidate answers based on the readability level.
-
公开(公告)号：US09916380B2
公开(公告)日：2018-03-13
申请号：US15159986
申请日：2016-05-20
发明人： Donna K. Byron , Devendra Goyal , Lakshminarayanan Krishnamurthy , Priscilla Santos Moraes , Michael C. Smith
CPC分类号： G06F17/30684 , G06F17/2705 , G06F17/273 , G06F17/274 , G06F17/2765 , G06F17/28 , G06F17/30719
摘要： Electronic natural language processing in a natural language processing (NLP) system, such as a Question-Answering (QA) system. A receives electronic text input, in question form, and determines a readability level indicator in the question. The readability level indicator includes at least a grammatical error, a slang term, and a misspelling type. The computer determines a readability level for the electronic text input based on the readability level indicator, and retrieves candidate answers based on the readability level.
-
公开(公告)号：US20170193091A1
公开(公告)日：2017-07-06
申请号：US14987827
申请日：2016-01-05
发明人： Donna K. Byron , Devendra Goyal , Lakshminarayanan Krishnamurthy , Priscilla Santos Moraes , Michael C. Smith
CPC分类号： G06F17/30684 , G06F17/2705 , G06F17/273 , G06F17/274 , G06F17/28 , G06F17/30719
摘要： Electronic natural language processing in a natural language processing (NLP) system, such as a Question-Answering (QA) system. A receives electronic text input, in question form, and determines a readability level indicator in the question. The readability level indicator includes at least a grammatical error, a slang term, and a misspelling type. The computer determines a readability level for the electronic text input based on the readability level indicator, and retrieves candidate answers based on the readability level.
-
公开(公告)号：US20170193090A1
公开(公告)日：2017-07-06
申请号：US14987816
申请日：2016-01-05
发明人： Donna K. Byron , Devendra Goyal , Lakshminarayanan Krishnamurthy , Priscilla Santos Moraes , Michael C. Smith
CPC分类号： G06F17/30684 , G06F17/2705 , G06F17/273 , G06F17/274 , G06F17/2765 , G06F17/28 , G06F17/30719
摘要： Electronic natural language processing in a natural language processing (NLP) system, such as a Question-Answering (QA) system. A receives electronic text input, in question form, and determines a readability level indicator in the question. The readability level indicator includes at least a grammatical error, a slang term, and a misspelling type. The computer determines a readability level for the electronic text input based on the readability level indicator, and retrieves candidate answers based on the readability level.
-
公开(公告)号：US11132370B2
公开(公告)日：2021-09-28
申请号：US16417090
申请日：2019-05-20
IPC分类号： G06F16/20 , G06F16/2457 , G06F16/248 , G06F16/28 , G06F16/33 , G06F16/34
摘要： Mechanisms are provided for implementing a candidate answer variant engine. The mechanisms receive an indication of a structured portion of content in a corpus, generate a plurality of groupings of elements of the structured portion of content, and generate, for each grouping of elements in the plurality of groupings of elements, and for each element in the grouping of elements, a corresponding grouping vector representation, corresponding to the element. The mechanisms, for each grouping vector representation of each grouping of elements in the plurality of groupings of elements perform a similarity measure calculation between the grouping vector representation and a vector representation of an input question, and select an element corresponding to the grouping vector representation for inclusion as a candidate answer variant based on results of the similarity measure calculation. The mechanisms perform question answering operations based on an analysis of one or more candidate answer variants.
-
公开(公告)号：US10482180B2
公开(公告)日：2019-11-19
申请号：US15816089
申请日：2017-11-17
IPC分类号： G06F17/27 , G06F17/24 , G06F16/332 , G06F16/33
摘要： Ground truth for a cognitive system is generated from a structured resource such as a table by identifying a subject of the structured resource and field headers. Linguistic analysis is performed on a given header to establish an interrogative context, and a question is generated relating to the subject based on the interrogative context, including an implementation of one or more mathematical operators. The question is generated using a question template, and has a question phrase based on the interrogative context, an operator phrase based on the selected operator, and a keyword phrase based on the subject. An answer to the question is determined by carrying out a computation that applies the selected operator(s) to one or more of the data values, to form a question-and-answer pair that is added to the ground truth. A filtering step is preferably used to ensure that the question-and-answer pair is valid.
-
公开(公告)号：US20190179840A1
公开(公告)日：2019-06-13
申请号：US16274663
申请日：2019-02-13
发明人： Donna K. Byron , Devendra Goyal , Lakshminarayanan Krishnamurthy , Priscilla Santos Moraes , Michael C. Smith
摘要： Electronic natural language processing in a natural language processing (NLP) system, such as a Question-Answering (QA) system. A receives electronic text input, in question form, and determines a readability level indicator in the question. The readability level indicator includes at least a grammatical error, a slang term, and a misspelling type. The computer determines a readability level for the electronic text input based on the readability level indicator, and retrieves candidate answers based on the readability level.
-
公开(公告)号：US20190155904A1
公开(公告)日：2019-05-23
申请号：US15816089
申请日：2017-11-17
CPC分类号： G06F17/2785 , G06F16/3329 , G06F16/3344 , G06F17/248 , G06F17/2765
摘要： Ground truth for a cognitive system is generated from a structured resource such as a table by identifying a subject of the structured resource and field headers. Linguistic analysis is performed on a given header to establish an interrogative context, and a question is generated relating to the subject based on the interrogative context, including an implementation of one or more mathematical operators. The question is generated using a question template, and has a question phrase based on the interrogative context, an operator phrase based on the selected operator, and a keyword phrase based on the subject. An answer to the question is determined by carrying out a computation that applies the selected operator(s) to one or more of the data values, to form a question-and-answer pair that is added to the ground truth. A filtering step is preferably used to ensure that the question-and-answer pair is valid.
-
公开(公告)号：US09858336B2
公开(公告)日：2018-01-02
申请号：US14987827
申请日：2016-01-05
发明人： Donna K. Byron , Devendra Goyal , Lakshminarayanan Krishnamurthy , Priscilla Santos Moraes , Michael C. Smith
CPC分类号： G06F17/30684 , G06F17/2705 , G06F17/273 , G06F17/274 , G06F17/28 , G06F17/30719
摘要： Electronic natural language processing in a natural language processing (NLP) system, such as a Question-Answering (QA) system. A receives electronic text input, in question form, and determines a readability level indicator in the question. The readability level indicator includes at least a grammatical error, a slang term, and a misspelling type. The computer determines a readability level for the electronic text input based on the readability level indicator, and retrieves candidate answers based on the readability level.
-
-
-
-
-
-
-
-
-
搜索结果
29 条记录 (耗时 0.022 秒)
