-
11.发明授权公开(公告)号：US10318634B2
公开(公告)日：2019-06-11
申请号：US15396712
申请日：2017-01-02
发明人： Bharath Dandala , Ravi S. Sinha
IPC分类号： G06F17/00 , G06F17/27 , G06F16/242 , G06F17/22 , G06F17/28
摘要： An approach is provided that returns a simplified set of text to a user of a natural language processing (NLP) system with the simplified set of text having a complexity appropriate to the reading level of the user. The approach receives a word that belongs to a first natural language and retrieves a first set of complexity data pertaining to the word in the first natural language. The approach translates the word to one or more translated words, with each of the translated words corresponding to one or more second natural languages. The approach then retrieves sets of complexity data, with the sets of complexity data corresponding to a different translated word. The approach determines a complexity of the word in the first natural language based on an analysis of the first and second sets of complexity data.
-
12.发明授权公开(公告)号：US10303765B2
公开(公告)日：2019-05-28
申请号：US15617407
申请日：2017-06-08
发明人： Bharath Dandala , Ravi S. Sinha
摘要： An approach is provided that returns a simplified set of text to a user of a natural language processing (NLP) system with the simplified set of text having a complexity appropriate to the reading level of the user. The approach receives a word that belongs to a first natural language and retrieves a first set of complexity data pertaining to the word in the first natural language. The approach translates the word to one or more translated words, with each of the translated words corresponding to one or more second natural languages. The approach then retrieves sets of complexity data, with the sets of complexity data corresponding to a different translated word. The approach determines a complexity of the word in the first natural language based on an analysis of the first and second sets of complexity data.
-
公开(公告)号：US10303764B2
公开(公告)日：2019-05-28
申请号：US15617377
申请日：2017-06-08
发明人： Bharath Dandala , Ravi S. Sinha
IPC分类号： G06F17/00 , G06F17/27 , G06F17/28 , G06F17/30 , G06F16/332
摘要： An approach is provided that receives a word that belongs to a first natural language and retrieves a first set of complexity data pertaining to the word in the first natural language. The approach translates the word to one or more translated words, with each of the translated words corresponding to one or more second natural languages. The approach then retrieves sets of complexity data, with the sets of complexity data corresponding to a different translated word. The approach determines a complexity of the word in the first natural language based on an analysis of the first and second sets of complexity data.
-
14.发明申请公开(公告)号：US20180189264A1
公开(公告)日：2018-07-05
申请号：US15617407
申请日：2017-06-08
发明人： Bharath Dandala , Ravi S. Sinha
CPC分类号： G06F17/277 , G06F17/2276 , G06F17/2795 , G06F17/2872 , G06F17/30401
摘要： An approach is provided that returns a simplified set of text to a user of a natural language processing (NLP) system with the simplified set of text having a complexity appropriate to the reading level of the user. The approach receives a word that belongs to a first natural language and retrieves a first set of complexity data pertaining to the word in the first natural language. The approach translates the word to one or more translated words, with each of the translated words corresponding to one or more second natural languages. The approach then retrieves sets of complexity data, with the sets of complexity data corresponding to a different translated word. The approach determines a complexity of the word in the first natural language based on an analysis of the first and second sets of complexity data.
-
公开(公告)号：US20180189263A1
公开(公告)日：2018-07-05
申请号：US15617377
申请日：2017-06-08
发明人： Bharath Dandala , Ravi S. Sinha
CPC分类号： G06F17/277 , G06F17/2785 , G06F17/289 , G06F17/30654
摘要： An approach is provided that receives a word that belongs to a first natural language and retrieves a first set of complexity data pertaining to the word in the first natural language. The approach translates the word to one or more translated words, with each of the translated words corresponding to one or more second natural languages. The approach then retrieves sets of complexity data, with the sets of complexity data corresponding to a different translated word. The approach determines a complexity of the word in the first natural language based on an analysis of the first and second sets of complexity data.
-
公开(公告)号：US20170351677A1
公开(公告)日：2017-12-07
申请号：US15172216
申请日：2016-06-03
IPC分类号： G06F17/30
CPC分类号： G06F16/24578 , G06F16/248 , G06F16/285 , G06F16/3344 , G06F16/345
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.
-
-
-
-
-
搜索结果
16 条记录 (耗时 0.019 秒)
