专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

71. 发明申请

US20100114558A1 Automatic Translation Method 有权
标题翻译：自动翻译方法
公开(公告)号：US20100114558A1
公开(公告)日：2010-05-06
申请号：US12532280
申请日：2008-03-12
申请人： Christian Fluhr , Gregory Grefenstette , Nasredlne Semmar
发明人： Christian Fluhr , Gregory Grefenstette , Nasredlne Semmar
IPC分类号： G06F17/28
CPC分类号： G06F17/2827 , G06F17/2845
摘要： The present invention relates to an automatic translation method.When a sentence in a source language is translated into a sentence in a target language, the method comprises: a step (1) of extracting the set of sentence portions of the target language from a textual database that correspond to a total or partial translation of the source sentence to be translated; a step (2) of determining all the assemblies of these target sentence portions that overlap the source sentence; a step (3) of choosing the best assemblies according to a criterion of maximum overlap between the target sentence portions assembled in the preceding step and according to a criterion of minimizing the number of assembled elements; a step (4) of determining the target sentence by choosing the best assembly according to coherence criteria. The invention is notably applicable to the translation of texts in a rare language.More generally, it applies to translation with no previously established bilingual texts.
摘要翻译：本发明涉及一种自动翻译方法。当源语言中的句子被翻译成目标语言的句子时，该方法包括：步骤（1）从对应于完全或部分翻译的文本数据库中提取目标语言的一组句子部分要翻译的源句; 确定与源语句重叠的目标句子部分的所有组合的步骤（2）; 根据在前述步骤中组装的目标句子部分之间的最大重叠的标准并根据最小化组装元件的数量的标准来选择最佳组件的步骤（3）通过根据相干标准选择最佳组合来确定目标句子的步骤（4）。本发明特别适用于以罕见语言翻译文本。更一般地说，它适用于没有既定双语文本的翻译。

72. 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

73. 发明申请

US20090119090A1 Principled Approach to Paraphrasing 审中-公开
标题翻译：改写原则的方法
公开(公告)号：US20090119090A1
公开(公告)日：2009-05-07
申请号：US11934010
申请日：2007-11-01
申请人： Cheng Niu , Ming Zhou
发明人： Cheng Niu , Ming Zhou
IPC分类号： G06F17/20
CPC分类号： G06F17/2827 , G06F16/3338 , G06F17/24 , G06F17/2795 , G06F17/2818
摘要： A principled approach to paraphrasing analyzes input text and paraphrases at atomic linguistic level, instead of analyzing the input text and paraphrases as a whole set at one time. The principled approach extracts atomic linguistic elements from the input text and identifies matching atomic paraphrasing elements to form candidate atomic paraphrasing pairs. A variety of atomic transformation types are identified to form atomic paraphrasing pairs. The candidate atomic paraphrasing pairs are evaluated using feature functions and a probability model. The principled approach scores a combination of multiple candidate atomic paraphrasing pairs using a score function which derives its value from the feature functions of the candidate atomic paraphrasing pairs. A combination which has a high score may be used for constructing a paraphrasing text.
摘要翻译：一种原则性的方法来解释分析输入文本和原子语言层面的释义，而不是一次分析整个输入文本和释义。原理方法从输入文本中提取原子语言元素，并识别匹配的原子释义元素以形成候选原子释义对。确定各种原子转换类型以形成原子释义对。使用特征函数和概率模型来评估候选原子释义对。原则性方法使用从候选原子释义对的特征函数导出其值的分数函数来评分多个候选原子释义对的组合。具有高分数的组合可以用于构造释义文本。

74. 发明申请

US20090112577A1 SYSTEM AND METHOD FOR LOCALIZATION OF ASSETS USING DICTIONARY FILE BUILD 有权
标题翻译：使用字幕文件构建资产本地化的系统和方法
公开(公告)号：US20090112577A1
公开(公告)日：2009-04-30
申请号：US12020113
申请日：2008-01-25
申请人： Bruce Gifford , Tadashi George Sakashita , Jonathan C. Scholtz
发明人： Bruce Gifford , Tadashi George Sakashita , Jonathan C. Scholtz
IPC分类号： G06F17/21
CPC分类号： G06F17/2827 , A63F13/54 , A63F13/60 , G06F9/454
摘要： A system and method for organizing localization content for video game development is disclosed. The method includes generating executable instructions for a video game being developed, wherein the video game is being developed for deployment in a plurality of natural languages, wherein text strings and/or multimedia data to be rendered during game play are referenced by the executable instructions. The method further includes identifiably storing the text strings and/or multimedia data in one or more dictionary files such that the text strings and/or multimedia data are identifiably referenced by references in the executable instructions and are identifiably referenced by a corresponding natural language.
摘要翻译：公开了一种用于组织视频游戏开发的本地化内容的系统和方法。该方法包括为正在开发的视频游戏生成可执行指令，其中，视频游戏正在被开发用于以多种自然语言部署，其中在游戏过程中呈现的文本串和/或多媒体数据被可执行指令所参考。该方法还包括将文本串和/或多媒体数据可识别地存储在一个或多个字典文件中，使得文本串和/或多媒体数据可由可执行指令中的引用识别地引用，并且可由相应的自然语言来标识。

75. 发明申请

US20090111585A1 SYSTEM AND METHOD OF LOCALIZING ASSETS USING TEXT SUBSTITUTIONS 有权
标题翻译：使用文本取代定位资产的系统和方法
公开(公告)号：US20090111585A1
公开(公告)日：2009-04-30
申请号：US12020021
申请日：2008-01-25
申请人： Tadashi George Sakashita , Bruce Gifford , Jonathan C. Scholtz
发明人： Tadashi George Sakashita , Bruce Gifford , Jonathan C. Scholtz
IPC分类号： A63F9/24
CPC分类号： G06F17/2827 , A63F13/54 , A63F13/60 , G06F9/454
摘要： A system and method for translating a phrase for video game development for games to be made available in a plurality of natural languages is disclosed. The method includes determining that code for a video game being developed has been created or modified. The method further includes inspecting the code to determine whether a phrase to be displayed or to be spoken during game play is present therein, wherein the phrase comprises a plurality of words. The method further includes comparing the entire phrase to a collection of phrases for which one or more translations to another natural language are already available, and if an exact match is determined, then reusing the one or more available translations for one or more corresponding languages.
摘要翻译：公开了一种用于翻译用于以多种自然语言提供的游戏的视频游戏开发的短语的系统和方法。该方法包括确定正在开发的视频游戏的代码已被创建或修改。该方法还包括检查代码以确定在游戏过程中是否要显示或要播放的短语，其中短语包括多个单词。该方法还包括将整个短语与一个或多个翻译到另一种自然语言已经可用的短语集合进行比较，如果确定了完全匹配，则对一个或多个对应语言重新使用一个或多个可用的翻译。

76. 发明申请

US20090094017A1 Multilingual Translation Database System and An Establishing Method Therefor 审中-公开
标题翻译：多语言翻译数据库系统及其建立方法
公开(公告)号：US20090094017A1
公开(公告)日：2009-04-09
申请号：US12332453
申请日：2008-12-11
申请人： Shing-Lung Chen , Chuan-Wen Chiang , Cheng-Sung Chang
发明人： Shing-Lung Chen , Chuan-Wen Chiang , Cheng-Sung Chang
IPC分类号： G06F17/28
CPC分类号： G06F17/2827
摘要： A method for building a multilingual translation database system includes the steps of: providing a plurality of multilingual sentence pairs or multilingual sentence-fragment pairs in a translation database, each of the multilingual sentence pairs or the multilingual sentence-fragment pairs formed with a source language and a target language; selecting repeated sentence structures or repeated sentence fragments from the multilingual sentence pairs or the multilingual sentence-fragment pairs; and defining or qualifying at least one repeated key sentence or key sentence fragment of the repeated sentence structures or the repeated key sentence-fragment structures with a predetermined degree of repeat frequency.
摘要翻译：一种用于构建多语言翻译数据库系统的方法，包括以下步骤：在翻译数据库中提供多个多语言句子对或多语言句子 - 片段对，每个多语言句子对或由源语言形成的多语言句子 - 片段对和目标语言; 从多语言句子对或多语言句子片段对中选择重复句子结构或重复句子片段; 并且以预定重复频率定义或限定重复句子结构或重复的关键句 - 片段结构的至少一个重复的关键句或关键句片段。

77. 发明申请

US20090083023A1 Means and Method for Adapted Language Translation 失效
标题翻译：适应语言翻译的手段和方法
公开(公告)号：US20090083023A1
公开(公告)日：2009-03-26
申请号：US11922311
申请日：2006-06-16
申请人： George Foster , Roland Kuhn
发明人： George Foster , Roland Kuhn
IPC分类号： G06F17/28
CPC分类号： G06F17/2827
摘要： This invention relates to a means and a method for translating source text into a target text where the context information is taken into consideration. A source text unit is defined around a translation unit which is to be translated. This source text unit is mapped onto a bilingual sublanguage space where the bilingual sublanguage space comprises a source sublanguage space and mappings to the target language. The translation is adapted to the source text unit, thereby considering contextual information.
摘要翻译：本发明涉及一种用于将源文本翻译成目标文本的手段和方法，其中考虑到上下文信息。源文本单元围绕要翻译的翻译单元被定义。该源文本单元被映射到双语子语言空间，其中双语子语言空间包括源子语言空间和与目标语言的映射。翻译适用于源文本单元，从而考虑上下文信息。

78. 发明申请

US20080147378A1 Online computer-aided translation 审中-公开
标题翻译：在线计算机辅助翻译
公开(公告)号：US20080147378A1
公开(公告)日：2008-06-19
申请号：US11953802
申请日：2007-12-10
申请人： Patrick J. Hall
发明人： Patrick J. Hall
IPC分类号： G06F17/28
CPC分类号： G06F17/2827
摘要： A source text in a source language is received. The source text is segmented into a plurality of segments. A first translation input, in a target language and associated with a first one of the segments, is received from a user. The first translation input is stored in a textual data repository.
摘要翻译：收到源语言的源文本。源文本被分割成多个段。从用户接收目标语言中的第一个翻译输入，并与第一个段相关联。第一个翻译输入存储在文本数据存储库中。

79. 发明申请

US20080120092A1 Phrase pair extraction for statistical machine translation 审中-公开
标题翻译：短语对提取用于统计机器翻译
公开(公告)号：US20080120092A1
公开(公告)日：2008-05-22
申请号：US11601992
申请日：2006-11-20
申请人： Robert C. Moore , Luke S. Zettlemoyer
发明人： Robert C. Moore , Luke S. Zettlemoyer
IPC分类号： G06F17/28
CPC分类号： G06F17/2827
摘要： In a machine translation system, possible phrase pairs are extracted from a word-aligned corpus for inclusion in a phrase translation table. Feature values associated with the phrase pairs are calculated and translation model parameters for use in a decoder are trained. The translation model parameters are then used to re-extract a subset of phrase pairs from the original set of extracted phrase pairs. The feature values associated with the subset of phrase pairs are recalculated, and the translation model parameters are re-optimized based on the newly extracted subset of phrase pairs and the feature values associated with those phrase pairs.
摘要翻译：在机器翻译系统中，从词对齐的语料库中提取可能的短语对以包含在短语翻译表中。计算与短语对相关联的特征值，并且训练在解码器中使用的翻译模型参数。然后，使用翻译模型参数从提取的短语对的原始集合中重新提取短语对的子集。重新计算与短语对的子集相关联的特征值，并且基于新提取的短语对的子集和与这些短语对相关联的特征值来重新计算翻译模型参数。

80. 发明申请

US20080109209A1 Semi-supervised training for statistical word alignment 有权
标题翻译：半监督统计词汇训练
公开(公告)号：US20080109209A1
公开(公告)日：2008-05-08
申请号：US11592450
申请日：2006-11-02
申请人： Alexander Fraser , Daniel Marcu
发明人： Alexander Fraser , Daniel Marcu
IPC分类号： G06F17/28
CPC分类号： G06F17/2827
摘要： A system and method for aligning words in parallel segments is provided. A first probability distribution of word alignments within a first corpus comprising unaligned word-level parallel segments according to a model estimate is calculated. The model estimate is modified according to the first probability distribution. One or more sub-models associated with the modified model estimate are discriminatively re-ranked according to word-level annotated parallel segments. A second probability distribution of the word alignments within the first corpus is calculated according to the re-ranked sub-models associated with the modified model estimate.
摘要翻译：提供了一种用于对齐并行段中的字的系统和方法。计算包括根据模型估计的非对齐字级并行段的第一语料库内的字对齐的第一概率分布。模型估计根据第一概率分布进行修改。与修改的模型估计相关联的一个或多个子模型根据字级注释的并行段被区分性地重新排序。根据与修改的模型估计相关联的重新排列的子模型来计算第一语料库内的单词对齐的第二概率分布。

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