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

EP1969493B1 ENCODING AND ADAPTIVE, SCALABLE ACCESSING OF DISTRIBUTED MODELS 有权转让
公开(公告)号：EP1969493B1
公开(公告)日：2018-12-26
申请号：EP07750990.9
申请日：2007-02-16
申请人： Google LLC
发明人： OCH, Franz , DEAN, Jeffrey , BRANTS, Thorsten , FRANZ, Alexander , PONTE, Jay , XU, Peng , TEH, Sha-Mayn , CHIN, Jeffrey , THAYER, Ignacio , CARVER, Anton , ROSART, Daniel , HAWKINS, John , DRIESEN, Karel
IPC分类号： G06F17/28
CPC分类号： G06F17/289 , G06F17/2818 , G06F17/2836 , G06F17/2845
摘要： Systems, methods, and apparatus for accessing distributed models in automated machine processing, including using large language models in machine translation, speech recognition and other applications.

32. 发明公开

EP2309397A1 DEVICE AND METHOD FOR SUPPORTING DETECTION OF MISTRANSLATION 审中-公开
标题翻译：用于支持检测转移的装置和方法
公开(公告)号：EP2309397A1
公开(公告)日：2011-04-13
申请号：EP09828981.2
申请日：2009-11-13
申请人： International Business Machines Corporation
发明人： MAEDERA Masahiko , SHIRATORI Takaaki
IPC分类号： G06F17/28
CPC分类号： G06F17/2836 , G06F17/277 , G06F17/2845
摘要： Object To efficiently detect words considered unsuitable as translated words in a specific field.
Solving Means In a client 10, a translation request unit 11 indicates to a translation engine 20 to translate an original document. A morphological analysis unit 13 performs morphological analysis on a translated document received from the translation engine 20 to extract compound words. A search request unit 15 inputs a search query that includes each of the extracted compound words to a search engine 30 to obtain the number α of exactly matching pages at a specific site, the number β of cooccurrence matching pages at the specific site, the number γ of exactly matching pages at all sites, and the number δ of cooccurrence matching pages at all sites. Then, an evaluation unit 17 classifies the compound word into a level indicating whether the compound word is suitable as a translated document in the specific site by comparing α or β with γ or δ. A dictionary update unit 19 updates a dictionary in the translation engine 20 in response to a request from a user based on display of the level.
摘要翻译：对象用于有效检测在特定字段中被认为不适合作为翻译词的词。解决手段在客户端10中，翻译请求单元11向翻译引擎20指示翻译原始文档。形态分析单元13对从翻译引擎20接收到的翻译文档执行形态分析以提取复合词。搜索请求单元15将包括提取的每个复合词的搜索查询输入到搜索引擎30，以获得特定站点处的精确匹配页面的数量α，特定站点处的共同出现匹配页面的数量β， γ在所有站点处完全匹配页面，以及在所有站点处共同出现匹配页面的数量δ。然后，评估单元17通过将α或β与γ或δ进行比较，将复合词分类为指示复合词是否适合作为特定位置中的翻译文档的水平。字典更新单元19响应于来自用户的基于电平的显示的请求而更新翻译引擎20中的字典。

33. 发明公开

EP2126735A1 PROCEDE DE TRADUCTION AUTOMATIQUE 审中-公开
标题翻译：自动翻译过程
公开(公告)号：EP2126735A1
公开(公告)日：2009-12-02
申请号：EP08717709.3
申请日：2008-03-12
申请人： Commissariat à l'Energie Atomique
发明人： FLUHR, Christian , GREFENSTETTE, Grégory , SEMMAR, Nasredine
IPC分类号： G06F17/28 , G06F17/30
CPC分类号： G06F17/2827 , G06F17/2845
摘要： The invention relates to an automatic translation method, in which a phrase in a source language is translated into a phrase in a target language, said method comprising: the step (1) of extracting the entire phrase portions in the target language into a text database corresponding to a total or partial translation of the source phrase to be translated; the step (2) of determining all the assemblies of the target phrase portions that cover the source phrase; the step (3) of selecting the best assemblies based on a maximal cover criterion between the target phrase portions assembled during the preceding step and based on a minimisation criterion of the number of assembled members; the step (4) of determining the target phrase by selecting the best assembly based on coherence criteria. The invention is particularly useful for translating texts in a rare language. More generally, the invention can be used for translations without previously established bilingual texts.

34. 发明公开

EP1217534A3 Method and apparatus for terminology translation 审中-公开
标题翻译：对于特定的术语翻译的方法和装置
公开(公告)号：EP1217534A3
公开(公告)日：2006-06-07
申请号：EP01129431.1
申请日：2001-12-10
申请人： Xerox Corporation
发明人： Hull, David
IPC分类号： G06F17/28
CPC分类号： G06F17/2818 , G06F17/2795 , G06F17/2836 , G06F17/2845
摘要： The invention relates to a method and apparatus for generating translations of natural language terms from a first language to a second language. A plurality of terms are extracted from unaligned comparable corpora of the first and second languages. Comparable corpora are sets of documents in different languages that come from the same domain and have similar genre and content. Unaligned documents are not translations of one another and are not linked in any other way. By accessing monolingual thesauri of the first and second languages, a category is assigned to each extracted term. Then, category-to-category translation probabilities are estimated, and using said category-to-category translation probabilities, term-to-term translation probabilities are estimated. The invention preferably exploits class-based normalization of probability estimates, bi-directionality, and relative frequency normalization. The most important applications are cross-language text retrieval, semi-automatic bilingual thesaurus enhancement, and machine-aided human translation.

35. 发明公开

EP2309397A4 DEVICE AND METHOD FOR SUPPORTING DETECTION OF MISTRANSLATION 审中-公开
标题翻译：用于支持错误翻译识别的装置和方法
公开(公告)号：EP2309397A4
公开(公告)日：2016-05-18
申请号：EP09828981
申请日：2009-11-13
申请人： IBM
发明人： MAEDERA MASAHIKO , SHIRATORI TAKAAKI
IPC分类号： G06F17/28 , G06F17/27
CPC分类号： G06F17/2836 , G06F17/277 , G06F17/2845

36. 发明公开

EP2102761A1 WEB-BASED COLLOCATION ERROR PROOFING 审中-公开
标题翻译：基于WEB的配置错误证明
公开(公告)号：EP2102761A1
公开(公告)日：2009-09-23
申请号：EP07854974.8
申请日：2007-12-05
申请人： Microsoft Corporation
发明人： GAO, Jianfeng , DOLAN, William B. , HON, Hsiao-Wuen , ZHOU, Ming
IPC分类号： G06F17/28
CPC分类号： G06F17/3061 , G06F17/273 , G06F17/277 , G06F17/2845
摘要： Collocation errors can be automatically proofed using local and network-based corpora, including the Web. For example, according to one illustrative method, one or more collocations from a text sample are compared with a corpus such as the content of the Web. The collocations are identified for whether they are disfavored in the corpus. Indications are provided via an output device of whether the collocations are disfavored in the corpus. Additional steps may then be taken such as searching for and providing potentially proper word collocations via a user output.
摘要翻译：搭配错误可以使用本地和基于网络的语料库（包括Web）自动校对。例如，根据一个说明性方法，来自文本样本的一个或多个搭配与诸如网络内容的语料库进行比较。确定搭配是否在语料库中不受欢迎。指示是通过输出设备提供语料库中搭配是否不受欢迎。然后可以采取额外的步骤，例如通过用户输出搜索并提供可能合适的词语搭配。

37. 发明公开

EP1483687A4 NAMED ENTITY TRANSLATION 审中-公开
标题翻译：翻译命名实体
公开(公告)号：EP1483687A4
公开(公告)日：2008-08-06
申请号：EP03714080
申请日：2003-03-11
申请人： UNIV SOUTHERN CALIFORNIA
发明人： AL-ONAIZAN YASER , KNIGHT KEVIN
IPC分类号： G06F17/27 , G06F17/28 , G06F17/22
CPC分类号： G06F17/278 , G06F17/2223 , G06F17/2818 , G06F17/2827 , G06F17/2845 , G06F17/2863
摘要： Translating named entities (110) from a source language to a target language. In general, in one implementation, the technique includes: generating potential translations of a named entity from a source language to a target language using a pronunciation-based and spelling-based transliteration model (210), searching a monolingual resource (220) in the target language for information relating to usage frequency, and providing output including at least one of the potential translations based on the usage frequency (230).

38. 发明公开

EP1576586A4 LANGUAGE TRANSLATION SYSTEM AND METHOD 审中-公开
标题翻译： SPRACHÜBERSETZUNGSSYSTEMUNDERVERHREN
公开(公告)号：EP1576586A4
公开(公告)日：2006-02-15
申请号：EP03783540
申请日：2003-11-14
申请人： TRANSCLICK INC
发明人： LEVIN ROBERT E
IPC分类号： G10L15/18 , G06F17/27 , G06F17/28 , G10L15/26 , H04L12/58 , H04W4/14 , H04W4/18
CPC分类号： G06F17/2735 , G06F17/2845 , G06F17/2872 , G06F17/289 , G10L15/1822 , H04L51/066 , H04W4/14 , H04W4/18
摘要： A system and method for translation of electronic communications automatically selects and deploys specialized dictionaries based upon context recognition and other factors. Software tools can be employed for continual dictionary enhancement. The invention can accept speech and text inputs and can be used to translate electronic mail, instant messages, chat, SMS messages, electronic text and word processing files, Internet web pages, Internet search results, and other textual communications for a variety of device types, including wireless devices. In one embodiment, language pairs are automatically determined in real-time.
摘要翻译：电子通信翻译系统和方法根据情境识别和其他因素自动选择和部署专门词典。软件工具可用于连续字典增强。本发明可以接受语音和文本输入，并且可以用于翻译电子邮件，即时消息，聊天，SMS消息，电子文本和文字处理文件，因特网网页，因特网搜索结果以及用于各种设备类型的其他文本通信，包括无线设备。在一个实施例中，语言对被实时地自动确定。

39. 发明公开

EP1588283A2 SYSTEM AND METHOD FOR LANGUAGE TRANSLATION VIA REMOTE DEVICES 审中-公开
标题翻译： VERFAHREN ZURSPRACHÜBERSETZUNGMITTELS ENTFERNTERGERÄTE系统
公开(公告)号：EP1588283A2
公开(公告)日：2005-10-26
申请号：EP03781965.3
申请日：2003-11-14
申请人： Transclick, Inc.
发明人： LEVIN, Robert, E.
IPC分类号： G06F17/28
CPC分类号： G06F17/2735 , G06F17/2845 , G06F17/2872 , G06F17/289 , G10L15/1822 , G10L2015/228 , H04L51/066 , H04W4/14 , H04W4/18
摘要： A system and method for translation of electronic communications automatically selects and deploys specialized dictionaries based upon context recognition and other factors. Software tools can be employed for continual dictionary enhancement. The invention can accept speech and text inputs and can be used to translate electronic mail, instant messages, chat, SMS messages, electronic text and word processing files, Internet web pages, Internet search results, and other textual communications for a variety of device types, including wireless devices. In one embodiment, language pairs are automatically determined in real-time.
摘要翻译：电子通信翻译系统和方法根据情境识别和其他因素自动选择和部署专门词典。软件工具可用于连续字典增强。本发明可以接受语音和文本输入，并且可以用于翻译电子邮件，即时消息，聊天，SMS消息，电子文本和文字处理文件，因特网网页，因特网搜索结果以及用于各种设备类型的其他文本通信，包括无线设备。在一个实施例中，语言对被实时地自动确定。

40. 发明公开

EP1217534A2 Method and apparatus for terminology translation 审中-公开
标题翻译： Verfahren und Apparat zur terminologie-spezifischenÜbersetzung
公开(公告)号：EP1217534A2
公开(公告)日：2002-06-26
申请号：EP01129431.1
申请日：2001-12-10
申请人： Xerox Corporation
发明人： Hull, David
IPC分类号： G06F17/28
CPC分类号： G06F17/2818 , G06F17/2795 , G06F17/2836 , G06F17/2845
摘要： The invention relates to a method and apparatus for generating translations of natural language terms from a first language to a second language. A plurality of terms are extracted from unaligned comparable corpora of the first and second languages. Comparable corpora are sets of documents in different languages that come from the same domain and have similar genre and content. Unaligned documents are not translations of one another and are not linked in any other way. By accessing monolingual thesauri of the first and second languages, a category is assigned to each extracted term. Then, category-to-category translation probabilities are estimated, and using said category-to-category translation probabilities, term-to-term translation probabilities are estimated. The invention preferably exploits class-based normalization of probability estimates, bi-directionality, and relative frequency normalization. The most important applications are cross-language text retrieval, semi-automatic bilingual thesaurus enhancement, and machine-aided human translation.
摘要翻译：本发明涉及一种用于从第一语言到第二语言产生自然语言术语的翻译的方法和装置。从第一语言和第二语言的不对齐可比语料库中提取多个术语。可比较的语料库是来自同一领域并具有相似类型和内容的不同语言的文档集合。未对齐的文档不是彼此的翻译，不以任何其他方式链接。通过访问第一和第二语言的单语词典，将一个类别分配给每个提取的项。然后，估计类别到类别的翻译概率，并且使用所述类别到类别的翻译概率来估计术语到期限的翻译概率。本发明优选地利用基于类的归一化概率估计，双向性和相对频率归一化。最重要的应用是跨语言文本检索，半自动双语词典增强和机器辅助人类翻译。

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