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. 发明授权

US06804637B1 Method, apparatus, and recording medium for retrieving optimum template pattern 有权
标题翻译：用于检索最佳模板图案的方法，装置和记录介质
公开(公告)号：US06804637B1
公开(公告)日：2004-10-12
申请号：US09597270
申请日：2000-06-20
申请人： Naoyuki Tokuda , Hiroyuki Sasai
发明人： Naoyuki Tokuda , Hiroyuki Sasai
IPC分类号： G06F1728
CPC分类号： G06F17/2836
摘要： To retrieve an optimum template pattern in response to an input sentence, a set of templates is arranged in a plurality of template blocks containing an arbitrary number of sentence components, including grammatically correct and/or incorrect components. A score is assigned to every word in the set of templates according to its importance. The candidate template patterns and the input sentence are retrieved, the scores of the matched words are calculated, and the total of the scores of the entire paths are calculated. Optimum level comparison values are then calculated using the score of the matching words as the numerator and the total score as the denominator. The candidate template pattern having the largest optimum level comparison value among optimum level comparison values that provide the largest numerator, is selected as the optimum template pattern. The input sentence is then corrected using this optimum template pattern.
摘要翻译：为了响应于输入句子来检索最佳模板模式，一组模板被布置在包含任意数量的句子分量的多个模板块中，包括语法上正确和/或不正确的组件。根据其重要性，将分数分配给模板集中的每个单词。检索候选模板模式和输入句子，计算匹配词的分数，并计算整个路径的得分总数。然后使用匹配词的分数作为分子和总分数作为分母来计算最佳水平比较值。选择提供最大分子的最佳电平比较值中具有最大最佳电平比较值的候选模板图案作为最佳模板图案。然后使用该最佳模板模式校正输入句子。

2. 依法登记的发明

USH2098H1 Multilingual communications device 失效
公开(公告)号：USH2098H1
公开(公告)日：2004-03-02
申请号：US08200049
申请日：1994-02-22
申请人： Lee M. E. Morin
发明人： Lee M. E. Morin
IPC分类号： G06F1728
摘要： A computer-based device for providing spoken translations of a predetermined set of medical questions, upon the selection of individual questions. Translations are prerecorded into a number of languages, and the physician user, in cooperation with the patient, chooses the language into which the translations are made. Then the physician chooses the questions in the physician's own language that should be asked, then indicates his choice to the device, and the device speaks the corresponding questions in the language of a potential respondent.

3. 发明授权

US06647364B1 Hypertext markup language document translating machine 有权
标题翻译：超文本标记语言文档翻译机
公开(公告)号：US06647364B1
公开(公告)日：2003-11-11
申请号：US09571315
申请日：2000-05-15
申请人： Takeshi Yumura , Naoyuki Yoden , Hiroki Ohnishi
发明人： Takeshi Yumura , Naoyuki Yoden , Hiroki Ohnishi
IPC分类号： G06F1728
CPC分类号： G06F17/289 , G06F17/21 , G06F17/2241 , G06F17/2264 , G06F17/30905
摘要： The present invention relates to a hypertext markup language (HTML) translating machine. The HTML translating machine automatically converts a HTML document with text described in a first language into a HTML document with text described in a second language.
摘要翻译：本发明涉及一种超文本标记语言（HTML）翻译机。 HTML翻译机自动将具有第一语言描述的文本的HTML文档转换成具有第二语言描述的文本的HTML文档。

4. 发明授权

US06629066B1 Method and system for building and running natural language understanding systems 有权
标题翻译：建立和运行自然语言理解系统的方法和系统
公开(公告)号：US06629066B1
公开(公告)日：2003-09-30
申请号：US09390457
申请日：1999-09-07
申请人： Eric G. Jackson , Michael H. Cohen , Fuliang Weng
发明人： Eric G. Jackson , Michael H. Cohen , Fuliang Weng
IPC分类号： G06F1728
CPC分类号： G06F17/2785 , G06F17/279
摘要： A computerized method for building and running natural language understanding systems, wherein a natural language understanding system takes a sentence as input and returns some representation of the possible meanings of the sentence as output (the “interpretation”) using a run-time interpreter th assigns interpretations to sentences and a compiler that produces (in a computer memory) an internal specification needed for the run-time interpreter from a user specification of the semantics of the application. The compiler builds a natural language system, while the run-time interpreter runs the system.
摘要翻译：一种用于构建和运行自然语言理解系统的计算机化方法，其中自然语言理解系统将句子作为输入，并且使用运行时解释器将所述句子的可能含义的一些表示作为输出（“解释”）返回对句子的解释以及从应用程序的语义的用户规范生成（在计算机存储器中）运行时解释器所需的内部规范的编译器。编译器构建自然语言系统，而运行时解释器则运行系统。

5. 发明授权

US06338033B1 System and method for network-based teletranslation from one natural language to another 失效
标题翻译：从一种自然语言到另一种自然语言的基于网络的电子翻译的系统和方法
公开(公告)号：US06338033B1
公开(公告)日：2002-01-08
申请号：US09294026
申请日：1999-04-20
申请人： Jean Bourbonnais , Martin Walker
发明人： Jean Bourbonnais , Martin Walker
IPC分类号： G06F1728
CPC分类号： G06F17/2836 , G06F17/273 , G06F17/289
摘要： A network-based teletranslation system and method for translating documents from one natural language to another natural language. The teletranslation system and method are capable of handling a wide variety of formats, including HTML documents from the Internet, intranets or extranets, e-mails, or electronic documents from a word processor or other applications. The teletranslation system and method are compatible with various MT engines and human translation services, and use the computing power of a network in a scalable and flexible way. The teletranslation system and method improve bandwidth and speed by distributing the workload among several computers in the network.
摘要翻译：一种基于网络的电子翻译系统和方法，用于将文档从一种自然语言翻译成另一种自然语言。电子翻译系统和方法能够处理各种格式，包括来自因特网的HTML文档，内部网或外部网，电子邮件或来自文字处理器或其他应用程序的电子文档。电台翻译系统和方法与各种MT引擎和人工翻译服务兼容，并以可扩展且灵活的方式使用网络的计算能力。电话翻译系统和方法通过在网络中的几台计算机之间分配工作负载来提高带宽和速度。

6. 发明授权

US06330529B1 Mark up language grammar based translation system 有权
标题翻译：标记语言语法的翻译系统
公开(公告)号：US06330529B1
公开(公告)日：2001-12-11
申请号：US09379792
申请日：1999-08-24
申请人： Etsuo Ito
发明人： Etsuo Ito
IPC分类号： G06F1728
CPC分类号： G06F17/272 , G06F17/289
摘要： A translation system and method of translating information, such as a homepage, written in a first language into a second language, when the information is written in accordance with a markup language grammar and provided by an information providing apparatus, such as a server computer connected to the Internet.
摘要翻译：当根据标记语言语法写入信息并由诸如连接的服务器计算机之类的信息提供装置提供的将第一语言的信息（例如主页）翻译成第二语言的翻译系统和方法到互联网。

7. 发明授权

US06285978B1 System and method for estimating accuracy of an automatic natural language translation 有权
标题翻译：自动语言翻译估计精度的系统和方法
公开(公告)号：US06285978B1
公开(公告)日：2001-09-04
申请号：US09159966
申请日：1998-09-24
申请人： Arendse Bernth , Claudia Maria Gdaniec , Michael Campbell McCord , Sue Ann Medeiros
发明人： Arendse Bernth , Claudia Maria Gdaniec , Michael Campbell McCord , Sue Ann Medeiros
IPC分类号： G06F1728
CPC分类号： G06F17/2854
摘要： A computer system and method for natural language translation uses a translation process to translate a source natural language segment (e.g. English) of one or more source words/elements into a target natural language (e.g. German) segment of one or more target words/elements. An evaluation module determines a confidence measure of the natural language translation. Typically, the confidence measure indicates less confidence as the complexity of the translation increases. Various novel features for determining complexity and confidence measure at different steps in the translation are used. The translation process can be terminated if the confidence measure fails to meet a threshold criterion.
摘要翻译：用于自然语言翻译的计算机系统和方法使用翻译过程将一个或多个源词/元素的源自然语言段（例如英语）翻译成一个或多个目标词/元素的目标自然语言（例如德语）段。评估模块确定自然语言翻译的置信度量度。通常，随着翻译的复杂性增加，置信度量表示较少的置信度。使用用于在平移中的不同步骤确定复杂度和置信度度量的各种新颖特征。如果置信度量度不符合阈值标准，则可以终止翻译过程。

8. 发明授权

US06275789B1 Method and apparatus for performing full bidirectional translation between a source language and a linked alternative language 有权
标题翻译：用于在源语言和链接的替代语言之间执行完全双向翻译的方法和装置
公开(公告)号：US06275789B1
公开(公告)日：2001-08-14
申请号：US09215425
申请日：1998-12-18
申请人： Leo Moser , Robert Moser
发明人： Leo Moser , Robert Moser
IPC分类号： G06F1728
CPC分类号： G06F17/2872 , G06F17/271 , G06F17/2775 , G06F17/2785
摘要： System with apparatus to improve international and other communication, and to provide easier access to data, especially digitized data, by means of linked alternative languages generated from a source language. As taught by the present invention, a linked alternative language is an especially designed language form quite different in outward format from its source language in that it has been optimized in a plurality of ways to allow targeted populations to comprehend and use it more efficiently than the source language, but which has also been carefully designed to retain full bidirectional machine translation equivalence to the source language. All use of artificial intelligence and computational linguistics for machine translation as taught in the present invention is constrained by these considerations.
摘要翻译：具有改进国际和其他通信的设备的系统，并通过从源语言生成的链接的替代语言来更容易地访问数据，特别是数字化数据。如本发明所教导的，链接的替代语言是一种特别设计的与其源语言不同外形格式的语言形式，因为它已经以多种方式被优化，以允许目标人群更有效地理解和使用它源语言，但也经过精心设计，以保持与源语言的完全双向机器翻译等价。对于本发明所教导的机器翻译的人造智能和计算语言学的所有使用都受到这些考虑的限制。

9. 发明授权

US06219632B1 System for the facilitation of supporting multiple concurrent languages through the use of semantic knowledge representation 失效
标题翻译：通过使用语义知识表示来促进支持多种并发语言的系统
公开(公告)号：US06219632B1
公开(公告)日：2001-04-17
申请号：US08974777
申请日：1997-11-20
申请人： John F. Schumacher , Robert Anthony Weida , Steffen Michael Fohn , Tomi Magome , Richard Bruce Humphrey
发明人： John F. Schumacher , Robert Anthony Weida , Steffen Michael Fohn , Tomi Magome , Richard Bruce Humphrey
IPC分类号： G06F1728
CPC分类号： G06F17/279 , G06F17/2872
摘要： A hierarchical knowledge representation is used in order to more efficiently support the translation and management of multiple localities. Utilizing this type of knowledge representation provides several key advantages. The first is a greater ability to differentiate semantically different symbols within the system. The second, is the ability to reutilize the translation of these symbols once translated a single time; and concurrent locale support.
摘要翻译：为了更有效地支持多个地方的翻译和管理，使用分级知识表示。利用这种类型的知识表示提供了几个关键优点。第一个是在系统中区分语义上不同的符号的更大能力。第二，是一次翻译一次翻译这些符号的翻译的能力; 并发地区支持。

10. 发明授权

US06195631B1 Method and apparatus for automatic construction of hierarchical transduction models for language translation 有权
标题翻译：自动构建语言翻译分层转换模型的方法和装置
公开(公告)号：US06195631B1
公开(公告)日：2001-02-27
申请号：US09198109
申请日：1998-11-23
申请人： Hiyan Alshawi , Shona Douglas
发明人： Hiyan Alshawi , Shona Douglas
IPC分类号： G06F1728
CPC分类号： G06F17/2827
摘要： A method and apparatus for automatically constructing hierarchical transduction models for language translation is presented. The input to the construction process may be a database of examples each consisting of a transcribed speech utterance and its translation into another language. A translation pairing score is assigned (or computed) for translating a word in the source language into each of the possible translations it has in the target language. For each instance of the resulting training dataset, a head transducer may be constructed that translates the source string into the target string by splitting the source string into a source head word, the words preceding the source head word, and the words following the source head word. This process may be performed recursively to generate a set of transducer fragments. The transducer fragments may form a statistical head transducer model. The head transducer translation model may then be input into a transduction search module.
摘要翻译：提出了一种自动构建语言翻译分层转换模型的方法和装置。对施工过程的输入可以是每个由转录的语音说话和其翻译成另一种语言的例子的数据库。分配（或计算）用于将源语言中的单词翻译成目标语言中的每个可能的翻译的翻译配对分数。对于所得到的训练数据集的每个实例，可以构造头传感器，其通过将源字符串分割成源头字，源头字前面的字和源头之后的字，将源字符串转换为目标字符串字。该过程可以递归地执行以产生一组换能器碎片。传感器碎片可以形成统计头传感器模型。然后可以将头部换能器转换模型输入到换能搜索模块中。

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