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. 再颁专利

USRE44722E1 Efficient use of exceptions in text segmentation 有权
标题翻译：在文本分割中有效地使用异常
公开(公告)号：USRE44722E1
公开(公告)日：2014-01-21
申请号：US13608446
申请日：2012-09-10
申请人： Enyuan Wu , Alan K. Michael , Marcus A. Taylor , Beom Seok Oh , Shusuke Uehara
发明人： Enyuan Wu , Alan K. Michael , Marcus A. Taylor , Beom Seok Oh , Shusuke Uehara
IPC分类号： G06F17/20 , G06F17/27
摘要： Input text may be broken into sentence, or other types of segments, by first detecting exceptions in the input text, and then detecting break positions. Given a segment breaking scheme that comprises a set of break rules and a set of exceptions, a regular expression is created that represents the break rules, and another regular expression is created that represents the exceptions. The input text is analyzed to identify strings that match any exception, and the matching strings are substituted with placeholders that are not likely to occur naturally in the input. The resulting text, with substitutions, is then evaluated to find the positions in the text that match the break rules. Those positions are declared to be segment breaks, and the placeholders are then replaced with the original strings. The result is the original text, with breaks assigned to the appropriate positions in the text.
摘要翻译：通过首先检测输入文本中的异常，然后检测断点位置，将输入文本分解成句子或其他类型的段。给定一个包含一组中断规则和一组异常的分段断开方案，创建一个表示断点规则的正则表达式，并创建另一个表示异常的正则表达式。分析输入文本以识别与任何异常相匹配的字符串，并且匹配的字符串将替换为不太可能在输入中自然发生的占位符。然后评估产生的带有替换的文本，以查找与断点规则匹配的文本中的位置。这些职位被宣布为细分受众群，然后用原始字符串替换占位符。结果是原始文本，文本中分配给适当位置的中断。

2. 发明授权

US08086442B1 Efficient use of exceptions in text segmentation 有权
标题翻译：在文本分割中有效地使用异常
公开(公告)号：US08086442B1
公开(公告)日：2011-12-27
申请号：US12968348
申请日：2010-12-15
申请人： Enyuan Wu , Alan K. Michael , Marcus A. Taylor , Beom Seok Oh , Shusuke Uehara
发明人： Enyuan Wu , Alan K. Michael , Marcus A. Taylor , Beom Seok Oh , Shusuke Uehara
IPC分类号： G06F17/20 , G06F17/27
CPC分类号： G06F17/2294 , G06F17/2229
摘要： Input text may be broken into sentence, or other types of segments, by first detecting exceptions in the input text, and then detecting break positions. Given a segment breaking scheme that comprises a set of break rules and a set of exceptions, a regular expression is created that represents the break rules, and another regular expression is created that represents the exceptions. The input text is analyzed to identify strings that match any exception, and the matching strings are substituted with placeholders that are not likely to occur naturally in the input. The resulting text, with substitutions, is then evaluated to find the positions in the text that match the break rules. Those positions are declared to be segment breaks, and the placeholders are then replaced with the original strings. The result is the original text, with breaks assigned to the appropriate positions in the text.
摘要翻译：通过首先检测输入文本中的异常，然后检测断点位置，将输入文本分解成句子或其他类型的段。给定一个包含一组中断规则和一组异常的分段断开方案，创建一个表示断点规则的正则表达式，并创建另一个表示异常的正则表达式。分析输入文本以识别与任何异常相匹配的字符串，并且匹配的字符串将替换为不太可能在输入中自然发生的占位符。然后评估产生的带有替换的文本，以查找与断点规则匹配的文本中的位置。这些职位被宣布为细分受众群，然后用原始字符串替换占位符。结果是原始文本，文本中分配给适当位置的中断。

3. 发明申请

US20120143593A1 FUZZY MATCHING AND SCORING BASED ON DIRECT ALIGNMENT 审中-公开
标题翻译：基于直接对齐的FUZZY匹配和分割
公开(公告)号：US20120143593A1
公开(公告)日：2012-06-07
申请号：US12961878
申请日：2010-12-07
申请人： Enyuan Wu , Alan K. Michael , Beom Seok Oh , Shusuke Uehara , Kevin S. O'Donnell
发明人： Enyuan Wu , Alan K. Michael , Beom Seok Oh , Shusuke Uehara , Kevin S. O'Donnell
IPC分类号： G06F17/28
CPC分类号： G06F17/2836
摘要： Various embodiments provide a translation memory system that utilizes sentence-level fuzzy matching and a scoring algorithm based on direct alignment. In one or more embodiments, a fuzzy match scoring formula includes use of an edit operation definition to define various deductions that are computed as part of an overall score, an overall scoring algorithm, and word-level scoring and partial match definitions. A direct alignment algorithm finds a computed alignment between two sentences using a pair-wise difference matrix associated with a primary sentence and a comparison sentence. An overall algorithm identifies editing operations such as replacements, position swaps and adjustments for a final score calculation. Once final scores are calculated between the primary sentence and multiple comparison sentences, a primary/comparison sentence pair can be selected, based on the score, to serve as a basis for translating the primary sentence.
摘要翻译：各种实施例提供了一种利用句级模糊匹配的翻译记忆系统和基于直接对齐的评分算法。在一个或多个实施例中，模糊匹配评分公式包括使用编辑操作定义来定义作为整体得分的一部分计算的各种扣除，总体评分算法以及词级评分和部分匹配定义。直接对齐算法使用与主句和比较句相关联的成对差分矩阵来找到两个句子之间的计算对齐。总体算法识别编辑操作，例如替换，位置互换和最终得分计算的调整。一旦在主句和多个比较句子之间计算最终分数，可以基于分数来选择主/比较句对，以作为翻译主句的基础。

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