专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20190188271A1 SUPPORTING EVIDENCE RETRIEVAL FOR COMPLEX ANSWERS 审中-公开
公开(公告)号：US20190188271A1
公开(公告)日：2019-06-20
申请号：US15844289
申请日：2017-12-15
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： James William Murdock , Eun Ha , Chung-Wei Hang , Kazi Hasan , Nisarga Markandaiah , Christopher Munjal Nolan , Lin Pan , Sai Prathyusha Peddi , Mary Diane Swift
IPC分类号： G06F17/30
CPC分类号： G06F16/24578 , G06F16/24575 , G06F16/3329 , G06F16/3344
摘要： Systems and methods for generating answers to questions. One method includes receiving a question having question terms; identifying candidate answers to the question having answer terms; searching data sources to determine passages including either a question term or an answer term in the candidate answer; scoring the passages for candidate answers using a scoring mechanism, the scoring mechanism computing a first degree of relevance of the passage to the question terms, computing a second degree of relevance of the passage to the answer terms of one of the candidate answers, and determining a score for the passage by combining the first degree of relevance and the second degree of relevance; ranking candidate answers to the question based on the scores associated with the scoring each of the passages for each of the candidate answers; and providing an answer to the question based on ranking of the candidate answers.

2. 发明申请

US20150379010A1 Dynamic Concept Based Query Expansion 审中-公开
标题翻译：基于动态概念的查询扩展
公开(公告)号：US20150379010A1
公开(公告)日：2015-12-31
申请号：US14315118
申请日：2014-06-25
申请人： International Business Machines Corporation
发明人： Corville O. Allen , Sai Prathyusha Peddi , Shannon E. Watanabe
IPC分类号： G06F17/30
CPC分类号： G06F16/3338
摘要： An approach is provided expand queries processed by a question/answer (QA) system. In the approach, concepts are extracted from documents using natural language processing to identify the concepts included in passages found in the documents. The approach generates child level categories in a category hierarchy from the concepts and groups the child level categories into sets based on related concepts. The process creates parent categories from the sets and divides a corpus used by the QA system into a number of sub-corpora, with each of the sub-corpora corresponding to one of the child level categories. The approach answers questions posed to the QA system by identifying a child level category related to the question and searching the sub-corpora corresponding to the child level category.
摘要翻译：提供一种方法来扩展由问题/答案（QA）系统处理的查询。在这种方法中，概念是从使用自然语言处理的文档中提取出来的，以便识别文档中发现的段落中包含的概念。该方法从概念中生成类别层次中的子级别类别，并根据相关概念将子级别类别分组为集合。该过程从集合创建父类别，并将质量检查系统使用的语料库划分为多个子语料库，每个子语料库对应于其中一个子级别类别。该方法通过确定与该问题相关的子级别类别并搜索与子级别类别相对应的子语料库，来回答对质量检查系统提出的问题。

3. 发明授权

US10810215B2 Supporting evidence retrieval for complex answers 有权
公开(公告)号：US10810215B2
公开(公告)日：2020-10-20
申请号：US15844289
申请日：2017-12-15
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： James William Murdock, IV , Eun Ha , Chung-Wei Hang , Kazi Hasan , Nisarga Markandaiah , Christopher Munjal Nolan , Lin Pan , Sai Prathyusha Peddi , Mary Diane Swift
IPC分类号： G06F7/02 , G06F16/00 , G06F16/2457 , G06F40/30 , G06F16/332 , G06F16/33
摘要： Systems and methods for generating answers to questions. One method includes receiving a question having question terms; identifying candidate answers to the question having answer terms; searching data sources to determine passages including either a question term or an answer term in the candidate answer; scoring the passages for candidate answers using a scoring mechanism, the scoring mechanism computing a first degree of relevance of the passage to the question terms, computing a second degree of relevance of the passage to the answer terms of one of the candidate answers, and determining a score for the passage by combining the first degree of relevance and the second degree of relevance; ranking candidate answers to the question based on the scores associated with the scoring each of the passages for each of the candidate answers; and providing an answer to the question based on ranking of the candidate answers.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式