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. 发明授权

US07974963B2 Method and system for retrieving confirming sentences 有权
标题翻译：检索确认句子的方法和系统
公开(公告)号：US07974963B2
公开(公告)日：2011-07-05
申请号：US11187567
申请日：2005-07-22
申请人： Ming Zhou , Hua Wu , Yue Zhang , Jianfeng Gao , Chang-Ning Huang
发明人： Ming Zhou , Hua Wu , Yue Zhang , Jianfeng Gao , Chang-Ning Huang
IPC分类号： G06F17/00
CPC分类号： G06F17/3069 , Y10S707/99933
摘要： A method, computer readable medium and system are provided which retrieve confirming sentences from a sentence database in response to a query. A search engine retrieves confirming sentences from the sentence database in response to the query. IN retrieving the confirming sentences, the search engine defines indexing units based upon the query, with the indexing units including both lemma from the query and extended indexing units associated with the query. The search engine then retrieves a plurality of sentences from the sentence database using the defined indexing units as search parameters. A similarity between each of the plurality of retrieved sentences and the query is determined by the search engine, wherein each similarity is determined as a function of a linguistic weight of a term in the query. The search engine then ranks the plurality of retrieved sentences based upon the determined similarities.
摘要翻译：提供了一种方法，计算机可读介质和系统，其响应于查询从句子数据库中检索确认句子。搜索引擎响应于查询从句子数据库中检索确认句子。在检索确认语句中，搜索引擎基于查询来定义索引单元，索引单元包括来自查询的引理和与查询相关联的扩展索引单元。然后，搜索引擎使用定义的索引单元作为搜索参数从句子数据库中检索多个句子。由搜索引擎确定多个检索到的句子和查询中的每一个之间的相似度，其中每个相似度被确定为查询中的术语的语言权重的函数。然后，搜索引擎基于所确定的相似度对多个检索到的句子进行排序。

2. 发明授权

US07343280B2 Processing noisy data and determining word similarity 有权
标题翻译：处理噪声数据并确定单词相似度
公开(公告)号：US07343280B2
公开(公告)日：2008-03-11
申请号：US10611368
申请日：2003-07-01
申请人： Hua Wu , Ming Zhou , Chang-Ning Huang
发明人： Hua Wu , Ming Zhou , Chang-Ning Huang
IPC分类号： G06F17/21 , G06F17/27
CPC分类号： G06F17/2715
摘要： The present invention deals with noisy data not by eliminating low frequency dependency structures, but rather by weighting the dependency structures. The dependency structures are weighted to give less weight to dependency structures which are more likely incorrect and to give more weight to dependency structures which are more likely correct.
摘要翻译：本发明不是通过消除低频依赖结构来处理噪声数据，而是通过加权依赖结构来处理噪声数据。对依赖关系结构进行加权，以给予依赖结构更少的权重，这些结构更可能是不正确的，并且对依赖结构给予更多的权重，这些结构更可能是正确

3. 发明申请

US20050273318A1 Method and system for retrieving confirming sentences 有权
标题翻译：检索确认句子的方法和系统
公开(公告)号：US20050273318A1
公开(公告)日：2005-12-08
申请号：US11187567
申请日：2005-07-22
申请人： Ming Zhou , Hua Wu , Yue Zhang , Jianfeng Gao , Chang-Ning Huang
发明人： Ming Zhou , Hua Wu , Yue Zhang , Jianfeng Gao , Chang-Ning Huang
IPC分类号： G06K9/18 , G06F17/28 , G06F17/30 , G06F17/40 , G06K7/00 , G06F17/21
CPC分类号： G06F17/3069 , Y10S707/99933
摘要： A method, computer readable medium and system are provided which retrieve confirming sentences from a sentence database in response to a query. A search engine retrieves confirming sentences from the sentence database in response to the query. IN retrieving the confirming sentences, the search engine defines indexing units based upon the query, with the indexing units including both lemma from the query and extended indexing units associated with the query. The search engine then retrieves a plurality of sentences from the sentence database using the defined indexing units as search parameters. A similarity between each of the plurality of retrieved sentences and the query is determined by the search engine, wherein each similarity is determined as a function of a linguistic weight of a term in the query. The search engine then ranks the plurality of retrieved sentences based upon the determined similarities.
摘要翻译：提供了一种方法，计算机可读介质和系统，其响应于查询从句子数据库中检索确认句子。搜索引擎响应于查询从句子数据库中检索确认句子。在检索确认语句中，搜索引擎基于查询来定义索引单元，索引单元包括来自查询的引理和与查询相关联的扩展索引单元。然后，搜索引擎使用定义的索引单元作为搜索参数从句子数据库中检索多个句子。由搜索引擎确定多个检索到的句子和查询中的每一个之间的相似度，其中每个相似度被确定为查询中的术语的语言权重的函数。然后，搜索引擎基于所确定的相似度对多个检索到的句子进行排序。

4. 发明授权

US07194455B2 Method and system for retrieving confirming sentences 有权
标题翻译：检索确认句子的方法和系统
公开(公告)号：US07194455B2
公开(公告)日：2007-03-20
申请号：US10247596
申请日：2002-09-19
申请人： Ming Zhou , Hua Wu , Yue Zhang , Jianfeng Gao , Chang-Ning Huang
发明人： Ming Zhou , Hua Wu , Yue Zhang , Jianfeng Gao , Chang-Ning Huang
IPC分类号： G06F17/30
CPC分类号： G06F17/3069 , Y10S707/99933
摘要： A method, computer readable medium and system are provided which retrieve confirming sentences from a sentence database in response to a query. A search engine retrieves confirming sentences from the sentence database in response to the query. IN retrieving the confirming sentences, the search engine defines indexing units based upon the query, with the indexing units including both lemma from the query and extended indexing units associated with the query. The search engine then retrieves a plurality of sentences from the sentence database using the defined indexing units as search parameters. A similarity between each of the plurality of retrieved sentences and the query is determined by the search engine, wherein each similarity is determined as a function of a linguistic weight of a term in the query. The search engine then ranks the plurality of retrieved sentences based upon the determined similarities.
摘要翻译：提供了一种方法，计算机可读介质和系统，其响应于查询从句子数据库中检索确认句子。搜索引擎响应于查询从句子数据库中检索确认句子。在检索确认语句中，搜索引擎基于查询来定义索引单元，索引单元包括来自查询的引理和与查询相关联的扩展索引单元。然后，搜索引擎使用定义的索引单元作为搜索参数从句子数据库中检索多个句子。由搜索引擎确定多个检索到的句子和查询中的每一个之间的相似度，其中每个相似度被确定为查询中的术语的语言权重的函数。然后，搜索引擎基于所确定的相似度对多个检索到的句子进行排序。

5. 发明申请

US20050004790A1 Processing noisy data and determining word similarity 有权
标题翻译：处理噪声数据并确定单词相似度
公开(公告)号：US20050004790A1
公开(公告)日：2005-01-06
申请号：US10611368
申请日：2003-07-01
申请人： Hua Wu , Ming Zhou , Chang-Ning Huang
发明人： Hua Wu , Ming Zhou , Chang-Ning Huang
IPC分类号： G06F17/27
CPC分类号： G06F17/2715
摘要： The present invention deals with noisy data not by eliminating low frequency dependency structures, but rather by weighting the dependency structures. The dependency structures are weighted to give less weight to dependency structures which are more likely incorrect and to give more weight to dependency structures which are more likely correct.
摘要翻译：本发明不是通过消除低频依赖结构来处理噪声数据，而是通过加权依赖结构来处理噪声数据。对依赖关系结构进行加权，以给予依赖结构更少的权重，这些结构更可能是不正确的，并且对依赖结构给予更多的权重，这些结构更可能是正确

6. 发明申请

US20050071149A1 System and method for identifying base noun phrases 有权
公开(公告)号：US20050071149A1
公开(公告)日：2005-03-31
申请号：US10977979
申请日：2004-10-29
申请人： Endong Xun , Ming Zhou , Chang-Ning Huang
发明人： Endong Xun , Ming Zhou , Chang-Ning Huang
IPC分类号： G06F17/27 , G06F17/28
CPC分类号： G06F17/271 , Y10S707/99932 , Y10S707/99933 , Y10S707/99934 , Y10S707/99935 , Y10S707/99936
摘要： A system and method identify base noun phrases (baseNP) in a linguistic input. A part-of-speech tagger identifies N-best part-of-speech tag sequences corresponding to the linguistic input. A baseNP identifier identifies baseNPs in the linguistic input using a unified statistical model that identifies the baseNPs, given the N-best POS sequences.

7. 发明授权

US07496501B2 System and method for identifying base noun phrases 有权
标题翻译：用于识别基础名词短语的系统和方法
公开(公告)号：US07496501B2
公开(公告)日：2009-02-24
申请号：US10977979
申请日：2004-10-29
申请人： Endong Xun , Ming Zhou , Chang-Ning Huang
发明人： Endong Xun , Ming Zhou , Chang-Ning Huang
IPC分类号： G06F17/27
CPC分类号： G06F17/271 , Y10S707/99932 , Y10S707/99933 , Y10S707/99934 , Y10S707/99935 , Y10S707/99936
摘要： A system and method identify base noun phrases (baseNP) in a linguistic input. A part-of-speech tagger identifies N-best part-of-speech tag sequences corresponding to the linguistic input. A baseNP identifier identifies baseNPs in the linguistic input using a unified statistical model that identifies the baseNPs, given the N-best POS sequences.
摘要翻译：系统和方法在语言输入中识别基础名词短语（baseNP）。词性标签器识别对应于语言输入的N个最佳词性标签序列。 baseNP标识符使用统一的统计模型识别语言输入中的baseNP，该统计模型鉴定了N个最佳POS序列。

8. 发明授权

US06859771B2 System and method for identifying base noun phrases 有权
标题翻译：用于识别基础名词短语的系统和方法
公开(公告)号：US06859771B2
公开(公告)日：2005-02-22
申请号：US09873656
申请日：2001-06-04
申请人： Endong Xun , Ming Zhou , Chang-Ning Huang
发明人： Endong Xun , Ming Zhou , Chang-Ning Huang
IPC分类号： G06F17/27 , G06F17/20
CPC分类号： G06F17/271 , Y10S707/99932 , Y10S707/99933 , Y10S707/99934 , Y10S707/99935 , Y10S707/99936
摘要： A system and method identify base noun phrases (baseNP) in a linguistic input. A part-of-speech tagger identifies N-best part-of-speech tag sequences corresponding to the linguistic input. A baseNP identifier identifies baseNPs in the linguistic input using a unified statistical model that identifies the baseNPs, given the N-best POS sequences.
摘要翻译：系统和方法在语言输入中识别基础名词短语（baseNP）。词性标签器识别对应于语言输入的N个最佳词性标签序列。 baseNP标识符使用统一的统计模型识别语言输入中的baseNP，该统计模型鉴定了N个最佳POS序列。

9. 发明授权

US07493251B2 Using source-channel models for word segmentation 有权
标题翻译：使用源通道模型进行分词
公开(公告)号：US07493251B2
公开(公告)日：2009-02-17
申请号：US10448644
申请日：2003-05-30
申请人： Jianfeng Gao , Mu Li , Chang-Ning Huang , Jian Sun , Lei Zhang , Ming Zhou
发明人： Jianfeng Gao , Mu Li , Chang-Ning Huang , Jian Sun , Lei Zhang , Ming Zhou
IPC分类号： G06F17/27 , G10L11/00
CPC分类号： G06F17/2755 , G06F17/277
摘要： A method and apparatus for segmenting text is provided that identifies a sequence of entity types from a sequence of characters and thereby identifies a segmentation for the sequence of characters. Under the invention, the sequence of entity types is identified using probabilistic models that describe the likelihood of a sequence of entities and the likelihood of sequences of characters given particular entities. Under one aspect of the invention, organization name entities are identified from a first sequence of identified entities to form a final sequence of identified entities.
摘要翻译：提供了用于分割文本的方法和装置，其从字符序列识别实体类型的序列，从而识别字符序列的分割。在本发明下，使用描述实体序列的可能性的概率模型和给定特定实体的字符序列的可能性来识别实体类型的序列。在本发明的一个方面，从识别的实体的第一序列识别组织名称实体，以形成所识别实体的最终序列。

10. 发明授权

US07689412B2 Synonymous collocation extraction using translation information 有权
标题翻译：使用翻译信息的同义搭配提取
公开(公告)号：US07689412B2
公开(公告)日：2010-03-30
申请号：US10729126
申请日：2003-12-05
申请人： Hua Wu , Ming Zhou
发明人： Hua Wu , Ming Zhou
IPC分类号： G06F17/21
CPC分类号： G06F17/2827 , G06F17/277
摘要： A method of automatically extracting synonymous collocations from monolingual corpora and a small bilingual corpus is proposed. The methodology includes generating candidate synonymous collocations and selecting synonymous collocations as a function of translation information, including collocation translations and probabilities. Candidate synonymous collocations with similarity scores that exceed a threshold are extracted as synonymous collocations. The extracted collocations can be used later in language generation by substituting synonymous collocations for applications such as writing assistance programs.
摘要翻译：提出了一种从单语语料库和小双语语料库自动提取同义词搭配的方法。该方法包括生成候选同义词搭配，并选择同义词搭配作为翻译信息的函数，包括搭配翻译和概率。具有超过阈值的相似性分数的候选同义词搭配被提取为同义词搭配。提取的搭配可以在语言生成中稍后用代替同义词搭配来应用程序，如写入辅助程序。

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