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

US20080243481A1 Large Language Models in Machine Translation 有权
标题翻译：机器翻译中的大语言模型
公开(公告)号：US20080243481A1
公开(公告)日：2008-10-02
申请号：US11767436
申请日：2007-06-22
申请人： Thorsten Brants , Ashok C. Popat , Peng Xu , Franz J. Och , Jeffrey Dean
发明人： Thorsten Brants , Ashok C. Popat , Peng Xu , Franz J. Och , Jeffrey Dean
IPC分类号： G06F17/27
CPC分类号： G06F17/2818 , G06F17/2827 , G06F17/2845
摘要： Systems, methods, and computer program products for machine translation are provided. In some implementations a system is provided. The system includes a language model including a collection of n-grams from a corpus, each n-gram having a corresponding relative frequency in the corpus and an order n corresponding to a number of tokens in the n-gram, each n-gram corresponding to a backoff n-gram having an order of n-1 and a collection of backoff scores, each backoff score associated with an n-gram, the backoff score determined as a function of a backoff factor and a relative frequency of a corresponding backoff n-gram in the corpus.
摘要翻译：提供了用于机器翻译的系统，方法和计算机程序产品。在一些实现中，提供了一种系统。该系统包括语言模型，其包括来自语料库的n-gram的集合，每个n-gram在语料库中具有对应的相对频率，并且n阶对应于n-gram中的令牌数量，每个n-gram对应到具有n-1级的退避n-gram和回退分数的集合，与n-gram相关联的每个回退分数，作为退避因子的函数确定的退避分数和相应退避n的相对频率 -gram在语料库中。

2. 发明授权

US08332207B2 Large language models in machine translation 有权
标题翻译：机器翻译中的大语言模型
公开(公告)号：US08332207B2
公开(公告)日：2012-12-11
申请号：US11767436
申请日：2007-06-22
申请人： Thorsten Brants , Ashok C. Popat , Peng Xu , Franz J. Och , Jeffrey Dean
发明人： Thorsten Brants , Ashok C. Popat , Peng Xu , Franz J. Och , Jeffrey Dean
IPC分类号： G06F17/27
CPC分类号： G06F17/2818 , G06F17/2827 , G06F17/2845
摘要： Systems, methods, and computer program products for machine translation are provided. In some implementations a system is provided. The system includes a language model including a collection of n-grams from a corpus, each n-gram having a corresponding relative frequency in the corpus and an order n corresponding to a number of tokens in the n-gram, each n-gram corresponding to a backoff n-gram having an order of n-1 and a collection of backoff scores, each backoff score associated with an n-gram, the backoff score determined as a function of a backoff factor and a relative frequency of a corresponding backoff n-gram in the corpus.
摘要翻译：提供了用于机器翻译的系统，方法和计算机程序产品。在一些实现中，提供了一种系统。该系统包括语言模型，其包括来自语料库的n-gram的集合，每个n-gram在语料库中具有相应的相对频率，并且n个对应于n-gram中的令牌数量的次序n，每个n-gram对应到具有n-1级的退避n-gram和回退分数的集合，与n-gram相关联的每个回退分数，作为退避因子的函数确定的退避分数和相应退避n的相对频率 -gram在语料库中。

3. 发明申请

US20130144592A1 Automatic Spelling Correction for Machine Translation 有权
标题翻译：机器翻译自动拼写修正
公开(公告)号：US20130144592A1
公开(公告)日：2013-06-06
申请号：US11850623
申请日：2007-09-05
申请人： Franz J. Och , Dmitriy Genzel
发明人： Franz J. Och , Dmitriy Genzel
IPC分类号： G06F17/28
CPC分类号： G06F17/28 , G06F17/273
摘要： Methods, systems, and apparatus, including computer program products, for correcting spelling in text. A text input is received for translation. One or more suspect words in the text input are identified. For each suspect word, one or more candidate words are identified. A score for the text input and scores for each of one or more candidate inputs are determined, where each candidate input is the text input with one or more of the suspect words each replaced by a respective candidate word. If any, a candidate input whose score is highest among the scores for the candidate inputs and is greater than the text input score by at least a threshold is selected. Otherwise, the text input is selected. A translation of a selected candidate input or the selected text input is provided as the translation of the text input.
摘要翻译：方法，系统和设备，包括计算机程序产品，用于纠正文本拼写。收到文本输入进行翻译。识别文本输入中的一个或多个可疑词。对于每个嫌疑词，识别一个或多个候选词。确定文本输入的分数和一个或多个候选输入中的每一个的分数，其中每个候选输入是文本输入，其中一个或多个可疑单词各自被相应的候选词替换。如果有的话，选择在候选输入的分数中得分最高并且大于文本输入得分至少一个阈值的候选输入。否则，选择文本输入。提供所选择的候选输入或所选择的文本输入的翻译作为文本输入的翻译。

4. 发明授权

US08626486B2 Automatic spelling correction for machine translation 有权
标题翻译：机器翻译自动拼写校正
公开(公告)号：US08626486B2
公开(公告)日：2014-01-07
申请号：US11850623
申请日：2007-09-05
申请人： Franz J. Och , Dmitriy Genzel
发明人： Franz J. Och , Dmitriy Genzel
IPC分类号： G06F17/28
CPC分类号： G06F17/28 , G06F17/273
摘要： Methods, systems, and apparatus, including computer program products, for correcting spelling in text. A text input is received for translation. One or more suspect words in the text input are identified. For each suspect word, one or more candidate words are identified. A score for the text input and scores for each of one or more candidate inputs are determined, where each candidate input is the text input with one or more of the suspect words each replaced by a respective candidate word. If any, a candidate input whose score is highest among the scores for the candidate inputs and is greater than the text input score by at least a threshold is selected. Otherwise, the text input is selected. A translation of a selected candidate input or the selected text input is provided as the translation of the text input.
摘要翻译：方法，系统和设备，包括计算机程序产品，用于纠正文本拼写。收到文本输入进行翻译。识别文本输入中的一个或多个可疑词。对于每个嫌疑词，识别一个或多个候选词。确定文本输入的分数和一个或多个候选输入中的每一个的分数，其中每个候选输入是文本输入，其中一个或多个可疑单词各自被相应的候选词替换。如果有的话，选择在候选输入的分数中得分最高并且大于文本输入得分至少一个阈值的候选输入。否则，选择文本输入。提供所选择的候选输入或所选择的文本输入的翻译作为文本输入的翻译。

5. 发明授权

US08185375B1 Word alignment with bridge languages 有权
标题翻译：与桥梁语言的字对齐
公开(公告)号：US08185375B1
公开(公告)日：2012-05-22
申请号：US11781824
申请日：2007-07-23
申请人： Shankar Kumar , Franz J. Och , Wolfgang Macherey
发明人： Shankar Kumar , Franz J. Och , Wolfgang Macherey
IPC分类号： G06F17/28
CPC分类号： G06F17/2818 , G06F17/2854
摘要： Systems, methods, and computer program products are provided for statistical machine translation. In some implementations a method is provided. The method includes receiving multi-lingual parallel text associating a source language, a target language, and one or more bridge languages, determining an alignment between the source language and the target language using a first bridge language that is distinct from the source language and the target language, and using the determined alignment to generate a candidate translation of an input text in the source language to the target language.
摘要翻译：系统，方法和计算机程序产品用于统计机器翻译。在一些实施方式中，提供了一种方法。该方法包括接收多语言并行文本，其将源语言，目标语言和一个或多个桥语言相关联，使用与源语言不同的第一桥语言来确定源语言和目标语言之间的对准，目标语言，以及使用所确定的对齐来产生源语言中的输入文本到目标语言的候选翻译。

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