专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

31. 发明授权

US07536295B2 Machine translation using non-contiguous fragments of text 失效
标题翻译：机器翻译使用不连续的文本片段
公开(公告)号：US07536295B2
公开(公告)日：2009-05-19
申请号：US11315043
申请日：2005-12-22
申请人： Nicola Cancedda , Bruno Cavestro , Marc Dymetman , Eric Gaussier , Cyril Goutte , Michel Simard , Kenji Yamada
发明人： Nicola Cancedda , Bruno Cavestro , Marc Dymetman , Eric Gaussier , Cyril Goutte , Michel Simard , Kenji Yamada
IPC分类号： G06F17/28
CPC分类号： G06F17/2827
摘要： A machine translation method for translating source text from a first language to target text in a second language includes receiving the source text in the first language and accessing a library of bi-fragments, each of the bi-fragments including a text fragment from the first language and a text fragment from the second language, at least some of the bi-fragments comprising non-contiguous bi-fragments in which at least one of the text fragment from the first language and the text fragment from the second language comprises a non-contiguous fragment.
摘要翻译：用于将源文本从第一语言翻译成以第二语言的目标文本的机器翻译方法包括以第一语言接收源文本并访问双片段的库，每个双片段包括来自第一语言的文本片段语言和来自第二语言的文本片段，至少一些双片段包括非连续双片段，其中来自第一语言的文本片段和来自第二语言的文本片段中的至少一个包含非连续双片段，连续片段

32. 发明授权

US09020804B2 Method for aligning sentences at the word level enforcing selective contiguity constraints 有权
标题翻译：用于在单词级别对齐句子的方法，强制选择性连续约束
公开(公告)号：US09020804B2
公开(公告)日：2015-04-28
申请号：US11756684
申请日：2007-06-01
申请人： Madalina Barbaiani , Nicola Cancedda , Christopher R. Dance , Szilárd Zsolt Fazekas , Tamás Gaál , Eric Gaussier
发明人： Madalina Barbaiani , Nicola Cancedda , Christopher R. Dance , Szilárd Zsolt Fazekas , Tamás Gaál , Eric Gaussier
IPC分类号： G06F17/28
CPC分类号： G06F17/2827
摘要： An alignment method includes, for a source sentence in a source language, identifying whether the sentence includes at least one candidate term comprising a contiguous subsequence of words of the source sentence. A target sentence in a target language is aligned with the source sentence. This includes developing a probabilistic model which models conditional probability distributions for alignments between words of the source sentence and words of the target sentence and generating an optimal alignment based on the probabilistic model, including, where the source sentence includes the at least one candidate term, enforcing a contiguity constraint which requires that all the words of the target sentence which are aligned with an identified candidate term form a contiguous subsequence of the target sentence.
摘要翻译：对准方法包括对于源语言的源语句，识别句子是否包括包括源语句的单词的连续子序列的至少一个候选词。目标语言中的目标句子与源语句对齐。这包括开发概率模型，其模拟条件概率分布，用于源语句的单词与目标句子的单词之间的对齐，并且基于概率模型产生最佳对齐，包括：源语句包括至少一个候选词，执行连续性约束，其要求与所识别的候选词对齐的目标句子的所有单词形成目标句子的连续子序列。

33. 发明授权

US08798984B2 Method and system for confidence-weighted learning of factored discriminative language models 有权
标题翻译：基于因子歧视语言模型的置信加权学习方法与系统
公开(公告)号：US08798984B2
公开(公告)日：2014-08-05
申请号：US13094999
申请日：2011-04-27
申请人： Nicola Cancedda , Viet Ha-Thuc
发明人： Nicola Cancedda , Viet Ha-Thuc
IPC分类号： G06F17/20 , G06F17/28 , G10L15/06
CPC分类号： G06F17/2818 , G10L15/06 , G10L15/197
摘要： A system and method for building a language model for a translation system are provided. The method includes providing a first relative ranking of first and second translations in a target language of a same source string in a source language, determining a second relative ranking of the first and second translations using weights of a language model, the language model including a weight for each of a set of n-gram features, and comparing the first and second relative rankings to determine whether they are in agreement. The method further includes, when the rankings are not in agreement, updating one or more of the weights in the language model as a function of a measure of confidence in the weight, the confidence being a function of previous observations of the n-gram feature in the method.
摘要翻译：提供了一种用于构建翻译系统的语言模型的系统和方法。该方法包括以源语言以相同源字符串的目标语言提供第一和第二翻译的第一相对排名，使用语言模型的权重确定第一和第二翻译的第二相对排名，该语言模型包括一组n-gram特征中的每一个的权重，并且比较第一和第二相对排名以确定它们是否一致。该方法还包括：当排名不一致时，将语言模型中的一个或多个权重作为权重中的置信度的函数来更新，所述置信度是n-gram特征的先前观察值的函数在该方法中。

34. 发明授权

US08775155B2 Machine translation using overlapping biphrase alignments and sampling 失效
标题翻译：机器翻译使用重叠的双峰对准和采样
公开(公告)号：US08775155B2
公开(公告)日：2014-07-08
申请号：US12911252
申请日：2010-10-25
申请人： Benjamin Roth , Andrew R. McCallum , Marc Dymetman , Nicola Cancedda
发明人： Benjamin Roth , Andrew R. McCallum , Marc Dymetman , Nicola Cancedda
IPC分类号： G06F17/28
CPC分类号： G06F17/2827 , G06F17/2818 , G06F17/2854
摘要： A system and method for machine translation are disclosed. Source sentences are received. For each source sentence, a target sentence comprising target words is generated. A plurality of translation neighbors of the target sentence is generated. Phrase alignments are computed between the source sentence and the translation neighbor. Translation neighbors are scored with a translation scoring model, based on the phrase alignment. Translation neighbors are ranked, based on the scores. In training the model, parameters of the model are updated based on an external ranking of the ranked translation neighbors. The generating of translation neighbors, scoring, ranking, and, in the case of training, updating the parameters, are iterated with one of the translation neighbors as the target sentence. In the case of decoding, one of the translation neighbors is output as a translation. The system and method may be at least partially implemented with a computer processor.
摘要翻译：公开了一种用于机器翻译的系统和方法。收到来源句子。对于每个源语句，生成包含目标词的目标句子。生成目标句子的多个翻译邻居。在源语句和翻译邻居之间计算短语对齐。翻译邻居用基于短语对齐的翻译评分模型进行评分。翻译邻居根据得分排名。在训练模型时，根据排名的翻译邻居的外部排名更新模型的参数。翻译邻居的产生，评分，排名，以及在培训的情况下更新参数，以翻译邻居之一作为目标句子迭代。在解码的情况下，翻译邻居中的一个作为翻译输出。系统和方法可以至少部分地用计算机处理器实现。

35. 发明授权

US08265923B2 Statistical machine translation employing efficient parameter training 有权
标题翻译：统计机器翻译采用有效的参数训练
公开(公告)号：US08265923B2
公开(公告)日：2012-09-11
申请号：US12777613
申请日：2010-05-11
申请人： Samidh Chatterjee , Nicola Cancedda
发明人： Samidh Chatterjee , Nicola Cancedda
IPC分类号： G06F17/28
CPC分类号： G06F17/2818
摘要： A statistical machine translation (SMT) system employs a conditional translation probability conditioned on the source language content. A model parameters optimization engine is configured to optimize values of parameters of the conditional translation probability using a translation pool comprising candidate aligned translations for source language sentences having reference translations. The model parameters optimization engine adds candidate aligned translations to the translation pool by sampling available candidate aligned translations in accordance with the conditional translation probability.
摘要翻译：统计机器翻译（SMT）系统采用以源语言内容为条件的条件翻译概率。模型参数优化引擎被配置为使用包括具有参考翻译的源语言句子的候选对齐翻译的翻译池来优化条件转换概率的参数值。模型参数优化引擎通过根据条件转换概率对候选对齐的翻译进行抽样来将候选对齐的翻译添加到翻译池。

36. 发明申请

US20120101804A1 MACHINE TRANSLATION USING OVERLAPPING BIPHRASE ALIGNMENTS AND SAMPLING 失效
标题翻译：机器翻译使用重叠的对比和采样
公开(公告)号：US20120101804A1
公开(公告)日：2012-04-26
申请号：US12911252
申请日：2010-10-25
申请人： Benjamin Roth , Andrew R. McCallum , Marc Dymetman , Nicola Cancedda
发明人： Benjamin Roth , Andrew R. McCallum , Marc Dymetman , Nicola Cancedda
IPC分类号： G06F17/28
CPC分类号： G06F17/2827 , G06F17/2818 , G06F17/2854
摘要： A system and method for machine translation are disclosed. Source sentences are received. For each source sentence, a target sentence comprising target words is generated. A plurality of translation neighbors of the target sentence is generated. Phrase alignments are computed between the source sentence and the translation neighbor. Translation neighbors are scored with a translation scoring model, based on the phrase alignment. Translation neighbors are ranked, based on the scores. In training the model, parameters of the model are updated based on an external ranking of the ranked translation neighbors. The generating of translation neighbors, scoring, ranking, and, in the case of training, updating the parameters, are iterated with one of the translation neighbors as the target sentence. In the case of decoding, one of the translation neighbors is output as a translation. The system and method may be at least partially implemented with a computer processor.
摘要翻译：公开了一种用于机器翻译的系统和方法。收到来源句子。对于每个源语句，生成包含目标词的目标句子。生成目标句子的多个翻译邻居。在源语句和翻译邻居之间计算短语对齐。翻译邻居用基于短语对齐的翻译评分模型进行评分。翻译邻居根据得分排名。在训练模型时，根据排名的翻译邻居的外部排名更新模型的参数。翻译邻居的产生，评分，排名，以及在培训的情况下更新参数，以翻译邻居之一作为目标句子迭代。在解码的情况下，翻译邻居中的一个作为翻译输出。系统和方法可以至少部分地用计算机处理器实现。

37. 发明申请

US20110307245A1 WORD ALIGNMENT METHOD AND SYSTEM FOR IMPROVED VOCABULARY COVERAGE IN STATISTICAL MACHINE TRANSLATION 有权
标题翻译：统计机器翻译中改进的词汇覆盖的字对齐方法和系统
公开(公告)号：US20110307245A1
公开(公告)日：2011-12-15
申请号：US12814657
申请日：2010-06-14
申请人： Gregory Alan Hanneman , Nicola Cancedda , Marc Dymetman
发明人： Gregory Alan Hanneman , Nicola Cancedda , Marc Dymetman
IPC分类号： G06F17/28
CPC分类号： G06F17/2827
摘要： A system and method for generating word alignments from pairs of aligned text strings are provided. A corpus of text strings provides pairs of text strings, primarily sentences, in source and target languages. A first alignment between a text string pair creates links therebetween. Each link links a single token of the first text string to a single token of the second text string. A second alignment also creates links between the text string pair. In some cases, these links may correspond to bi-phrases. A modified first alignment is generated by selectively modifying links in the first alignment which include a word which is infrequent in the corpus, based on links generated in the second alignment. This results in removing at least some of the links for the infrequent words, allowing more compact and better quality bi-phrases, with higher vocabulary coverage, to be extracted for use in a machine translation system.
摘要翻译：提供了用于从对齐的文本串对中生成字对齐的系统和方法。文本字符串的语料库以源语言和目标语言提供了一对文本字符串，主要是句子。文本串对之间的第一对齐在其间创建链接。每个链接将第一个文本字符串的单个标记链接到第二个文本字符串的单个标记。第二个对齐也创建文本串对之间的链接。在某些情况下，这些链接可能对应于双语短语。通过基于在第二对准中产生的链接，通过选择性地修改第一对齐中的链接来生成修改的第一对准，该链接包括语料库中不频繁的单词。这导致删除不频繁的单词的至少一些链接，允许提取具有较高词汇覆盖率的更紧凑和更好质量的双语短语以用于机器翻译系统。

38. 发明授权

US07647534B2 Method for avoiding repetition of user actions by using past users' experiences 有权
标题翻译：通过使用过去用户体验来避免重复用户操作的方法
公开(公告)号：US07647534B2
公开(公告)日：2010-01-12
申请号：US11378134
申请日：2006-03-17
申请人： Stefania Castellani , Nicola Cancedda , Maria Antonietta Grasso , Jacki O'Neill
发明人： Stefania Castellani , Nicola Cancedda , Maria Antonietta Grasso , Jacki O'Neill
IPC分类号： G06F11/00
CPC分类号： G06Q10/00 , G03G15/502 , G03G15/5075 , G03G15/55 , G03G2215/00109
摘要： A method for assisting a user to connect a problem with a device, such as a printer includes extracting, from records comprising user actions on the device, string of user actions on the device. The string of user action is compared with at least one predetermined sequence of user actions for correction of predefined problem with the device. Based on the comparison, an evaluation is made as to whether at least one prior user has attempted the predetermined sequence and, if so, a procedure is implemented to avoid a user repeating the prior attempt.
摘要翻译：用于辅助用户将问题与诸如打印机的设备连接的方法包括从包括设备上的用户动作的记录中提取在设备上的用户动作串。将用户操作串与至少一个预定的用户动作序列进行比较，以便用于校正与设备的预定义问题。基于比较，评估至少一个在先用户是否尝试了预定的序列，如果是，则实施一个过程以避免用户重复先前的尝试。

39. 发明申请

US20090175545A1 METHOD FOR COMPUTING SIMILARITY BETWEEN TEXT SPANS USING FACTORED WORD SEQUENCE KERNELS 有权
标题翻译：使用成功的词序列密码计算文本传播之间的相似性的方法
公开(公告)号：US20090175545A1
公开(公告)日：2009-07-09
申请号：US11969314
申请日：2008-01-04
申请人： Nicola Cancedda , Pierre Mahe
发明人： Nicola Cancedda , Pierre Mahe
IPC分类号： G06K9/72
CPC分类号： G06K9/726 , G06K9/627 , G06K2209/01
摘要： A computer implemented method and an apparatus for comparing spans of text are disclosed. The method includes computing a similarity measure between a first sequence of symbols representing a first text span and a second sequence of symbols representing a second text span as a function of the occurrences of optionally noncontiguous subsequences of symbols shared by the two sequences of symbols. Each of the symbols comprises at least one consecutive word and is defined according to a set of linguistic factors. Pairs of symbols in the first and second sequences that form a shared subsequence of symbols are each matched according to at least one of the factors.
摘要翻译：公开了一种用于比较文本跨度的计算机实现的方法和装置。所述方法包括计算表示第一文本跨度的第一符号序列和表示第二文本跨度的第二符号序列之间的相似性度量，作为由两个符号序列共享的符号的可选非连续的子序列的出现的函数。符号中的每一个包括至少一个连续字，并且根据一组语言因素来定义。形成符号的共享子序列的第一和第二序列中的符号对对应于至少一个因素。

40. 发明申请

US20070265825A1 Machine translation using elastic chunks 失效
标题翻译：机械翻译使用弹性块
公开(公告)号：US20070265825A1
公开(公告)日：2007-11-15
申请号：US11431393
申请日：2006-05-10
申请人： Nicola Cancedda , Marc Dymetman , Eric Gaussier , Cyril Goutte
发明人： Nicola Cancedda , Marc Dymetman , Eric Gaussier , Cyril Goutte
IPC分类号： G06F17/28
CPC分类号： G06F17/2818
摘要： A machine translation method includes receiving source text in a first language and retrieving text fragments in a target language from a library of bi-fragments to generate a target hypothesis. Each bi-fragment includes a text fragment from the first language and a corresponding text fragment from the second language. Some of the bi-fragments are modeled as elastic bi-fragments where a gap between words is able to assume a variable size corresponding to a number of other words to occupy the gap. The target hypothesis is evaluated with a translation scoring function which scores the target hypothesis according to a plurality of feature functions, at least one of the feature functions comprising a gap size scoring feature which favors hypotheses with statistically more probable gap sizes over hypotheses with statically less probable gap sizes.
摘要翻译：机器翻译方法包括以第一语言接收源文本并且从双片段的库中检索目标语言中的文本片段以生成目标假设。每个双片段包括来自第一语言的文本片段和来自第二语言的相应文本片段。一些双片段被建模为弹性双片段，其中词之间的间隙能够采用与多个其他单词相对应的可变大小来占据间隙。目标假设用翻译评分函数评估，其根据多个特征函数对目标假设进行评分，特征函数中的至少一个包括间隙大小评分特征，其有利于具有统计学上更可能的间隔大小超过假设的假设，具有静态较小可能的间隙大小。

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