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

US20060190241A1 Apparatus and methods for aligning words in bilingual sentences 失效
标题翻译：双语句子对齐词的装置和方法
公开(公告)号：US20060190241A1
公开(公告)日：2006-08-24
申请号：US11137590
申请日：2005-05-26
申请人： Cyril Goutte , Michel Simard , Kenji Yamada , Eric Gaussier , Arne Mauser
发明人： Cyril Goutte , Michel Simard , Kenji Yamada , Eric Gaussier , Arne Mauser
IPC分类号： G06F17/28
CPC分类号： G06F17/2827
摘要： Methods are disclosed for performing proper word alignment that satisfy constraints of coverage and transitive closure. Initially, a translation matrix which defines word association measures between source and target words of a corpus of bilingual translations of source and target sentences is computed. Subsequently, in a first method, the association measures in the translation matrix are factorized and orthogonalized to produce cepts for the source and target words, which resulting matrix factors may then be, optionally, multiplied to produce an alignment matrix. In a second method, the association measures in the translation matrix are thresholded, and then closed by transitivity, to produce an alignment matrix, which may then be, optionally, factorized to produce cepts. The resulting cepts or alignment matrices may then be used by any number of natural language applications for identifying words that are properly aligned.
摘要翻译：公开了用于执行满足覆盖和传递闭包约束的适当字对齐的方法。最初，计算了定义源语句和目标语句双语翻译语料库的源词和目标词之间的词关联度量的翻译矩阵。随后，在第一种方法中，翻译矩阵中的关联度量被分解和正交化以产生源词和目标词的尖叫，所得到的矩阵因子然后可以被乘以以产生对齐矩阵。在第二种方法中，翻译矩阵中的关联度量被阈值化，然后由传递性闭合，以产生对准矩阵，其可以随后被分解以产生尖叫。所得到的尖叫或对齐矩阵然后可以被任何数量的自然语言应用程序用于识别正确对准的单词。

2. 发明授权

US07672830B2 Apparatus and methods for aligning words in bilingual sentences 失效
标题翻译：双语句子对齐词的装置和方法
公开(公告)号：US07672830B2
公开(公告)日：2010-03-02
申请号：US11137590
申请日：2005-05-26
申请人： Cyril Goutte , Michel Simard , Kenji Yamada , Eric Gaussier , Arne Mauser
发明人： Cyril Goutte , Michel Simard , Kenji Yamada , Eric Gaussier , Arne Mauser
IPC分类号： G06F17/28 , G06F17/27
CPC分类号： G06F17/2827
摘要： Methods are disclosed for performing proper word alignment that satisfy constraints of coverage and transitive closure. Initially, a translation matrix which defines word association measures between source and target words of a corpus of bilingual translations of source and target sentences is computed. Subsequently, in a first method, the association measures in the translation matrix are factorized and orthogonalized to produce cepts for the source and target words, which resulting matrix factors may then be, optionally, multiplied to produce an alignment matrix. In a second method, the association measures in the translation matrix are thresholded, and then closed by transitivity, to produce an alignment matrix, which may then be, optionally, factorized to produce cepts. The resulting cepts or alignment matrices may then be used by any number of natural language applications for identifying words that are properly aligned.
摘要翻译：公开了用于执行满足覆盖和传递闭包约束的适当字对齐的方法。最初，计算了定义源语句和目标语句双语翻译语料库的源词和目标词之间的词关联度量的翻译矩阵。随后，在第一种方法中，翻译矩阵中的关联度量被分解和正交化以产生源词和目标词的尖叫，所得到的矩阵因子然后可以被乘以以产生对齐矩阵。在第二种方法中，翻译矩阵中的关联度量被阈值化，然后由传递性闭合，以产生对准矩阵，其可以随后被分解以产生尖叫。所得到的尖叫或对齐矩阵然后可以被任何数量的自然语言应用程序用于识别正确对准的单词。

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