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

US5477451A Method and system for natural language translation 失效
标题翻译：自然语言翻译方法与系统
公开(公告)号：US5477451A
公开(公告)日：1995-12-19
申请号：US736278
申请日：1991-07-25
申请人： Peter F. Brown , John Cocke , Stephen A. Della Pietra , Vincent J. Della Pietra , Frederick Jelinek , Jennifer C. Lai , Robert L. Mercer
发明人： Peter F. Brown , John Cocke , Stephen A. Della Pietra , Vincent J. Della Pietra , Frederick Jelinek , Jennifer C. Lai , Robert L. Mercer
IPC分类号： G10L15/14 , G06F17/27 , G06F17/28 , G10L15/00 , G06F17/20
CPC分类号： G06F17/2818 , G06F17/2755 , G06F17/2845 , G06F17/2872
摘要： The present invention is a system for translating text from a first source language into a second target language. The system assigns probabilities or scores to various target-language translations and then displays or makes otherwise available the highest scoring translations. The source text is first transduced into one or more intermediate structural representations. From these intermediate source structures a set of intermediate target-structure hypotheses is generated. These hypotheses are scored by two different models: a language model which assigns a probability or score to an intermediate target structure, and a translation model which assigns a probability or score to the event that an intermediate target structure is translated into an intermediate source structure. Scores from the translation model and language model are combined into a combined score for each intermediate target-structure hypothesis. Finally, a set of target-text hypotheses is produced by transducing the highest scoring target-structure hypotheses into portions of text in the target language. The system can either run in batch mode, in which case it translates source-language text into a target language without human assistance, or it can function as an aid to a human translator. When functioning as an aid to a human translator, the human may simply select from the various translation hypotheses provided by the system, or he may optionally provide hints or constraints on how to perform one or more of the stages of source transduction, hypothesis generation and target transduction.
摘要翻译：本发明是用于将文本从第一源语言翻译成第二目标语言的系统。系统将概率或分数分配给各种目标语言翻译，然后显示或使其他可用的最高得分翻译。源文本首先被转换成一个或多个中间结构表示。从这些中间源结构生成一组中间目标结构假设。这些假设用两种不同的模型进行评分：将中间目标结构分配概率或分数的语言模型，以及将中间目标结构转换为中间源结构的事件分配概率或分数的翻译模型。翻译模型和语言模型的得分被组合为每个中间目标结构假说的综合得分。最后，通过将目标语言文本的最高得分目标结构假设转换为部分文本来产生一组目标文本假设。该系统可以以批处理模式运行，在这种情况下，它将源语言文本转换为目标语言，而无需人工帮助，或者可以作为人类翻译器的辅助功能。人类可以简单地从系统提供的各种翻译假设中进行选择，或者可选择地提供关于如何执行源转换，假设生成的一个或多个阶段的提示或限制，靶转导。

2. 发明授权

US5293584A Speech recognition system for natural language translation 失效
标题翻译：自然语言翻译语音识别系统
公开(公告)号：US5293584A
公开(公告)日：1994-03-08
申请号：US887205
申请日：1992-05-21
申请人： Peter F. Brown , Stephen A. Della Pietra , Vincent J. Della Pietra , Frederick Jelinek , Robert L. Mercer
发明人： Peter F. Brown , Stephen A. Della Pietra , Vincent J. Della Pietra , Frederick Jelinek , Robert L. Mercer
IPC分类号： G10L15/18 , G10L5/00
CPC分类号： G10L15/18
摘要： A speech recognition system displays a source text of one or more words in a source language. The system has an acoustic processor for generating a sequence of coded representations of an utterance to be recognized. The utterance comprises a series of one or more words in a target language different from the source language. A set of one or more speech hypotheses, each comprising one or more words from the target language, are produced. Each speech hypothesis is modeled with an acoustic model. An acoustic match score for each speech hypothesis comprises an estimate of the closeness of a match between the acoustic model of the speech hypothesis and the sequence of coded representations of the utterance. A translation match score for each speech hypothesis comprises an estimate of the probability of occurrence of the speech hypothesis given the occurrence of the source text. A hypothesis score for each hypothesis comprises a combination of the acoustic match score and the translation match score. At least one word of one or more speech hypotThis invention was made with Government support under Contract Number N00014-91-C-0135 awarded by the office of Naval Research. The Government has certain rights in this invention.
摘要翻译：语音识别系统以源语言显示一个或多个单词的源文本。该系统具有声学处理器，用于产生要识别的话语的编码表示序列。话语包括与源语言不同的目标语言中的一系列一个或多个单词。产生一组一个或多个语音假设，每个语音假设包括来自目标语言的一个或多个单词。每个言语假说都用声学模型建模。每个语音假设的声匹配分数包括语音假设的声学模型与语音的编码表示序列之间的匹配的接近度的估计。每个语音假设的翻译匹配分数包括给定源文本的出现的语音假设的发生概率的估计。每个假设的假设得分包括声匹配分数和翻译匹配分数的组合。输出具有最佳假设得分的一个或多个语音假设的至少一个字作为识别结果。

3. 发明授权

US5805832A System for parametric text to text language translation 失效
标题翻译：用于文本语言翻译的参数文本系统
公开(公告)号：US5805832A
公开(公告)日：1998-09-08
申请号：US459454
申请日：1995-06-02
申请人： Peter Fitzhugh Brown , John Cocke , Stephen Andrew Della Pietra , Vincent Joseph Della Pietra , Frederick Jelinek , Jennifer Ceil Lai , Robert Leroy Mercer
发明人： Peter Fitzhugh Brown , John Cocke , Stephen Andrew Della Pietra , Vincent Joseph Della Pietra , Frederick Jelinek , Jennifer Ceil Lai , Robert Leroy Mercer
IPC分类号： G10L15/14 , G06F17/27 , G06F17/28 , G10L15/00
CPC分类号： G06F17/2818 , G06F17/2755 , G06F17/2845 , G06F17/2872
摘要： The present invention is a system for translating text from a first source language into a second target language. The system assigns probabilities or scores to various target-language translations and then displays or makes otherwise available the highest scoring translations. The source text is first transduced into one or more intermediate structural representations. From these intermediate source structures a set of intermediate target-structure hypotheses is generated. These hypotheses are scored by two different models: a language model which assigns a probability or score to an intermediate target structure, and a translation model which assigns a probability or score to the event that an intermediate target structure is translated into an intermediate source structure. Scores from the translation model and language model are combined into a combined score for each intermediate target-structure hypothesis. Finally, a set of target-text hypotheses is produced by transducing the highest scoring target-structure hypotheses into portions of text in the target language. The system can either run in batch mode, in which case it translates source-language text into a target language without human assistance, or it can function as an aid to a human translator. When functioning as an aid to a human translator, the human may simply select from the various translation hypotheses provided by the system, or he may optionally provide hints or constraints on how to perform one or more of the stages of source transduction, hypothesis generation and target transduction.
摘要翻译：本发明是用于将文本从第一源语言翻译成第二目标语言的系统。系统将概率或分数分配给各种目标语言翻译，然后显示或使其他可用的最高得分翻译。源文本首先被转换成一个或多个中间结构表示。从这些中间源结构生成一组中间目标结构假设。这些假设用两种不同的模型进行评分：将中间目标结构分配概率或分数的语言模型，以及将中间目标结构转换为中间源结构的事件分配概率或分数的翻译模型。翻译模型和语言模型的得分被组合为每个中间目标结构假说的综合得分。最后，通过将目标语言文本的最高得分目标结构假设转换为部分文本来产生一组目标文本假设。该系统可以以批处理模式运行，在这种情况下，它将源语言文本转换为目标语言，而无需人工帮助，或者可以作为人类翻译器的辅助功能。人类可以简单地从系统提供的各种翻译假设中进行选择，或者可选择地提供关于如何执行源转换，假设生成的一个或多个阶段的提示或限制，靶转导。

4. 发明授权

US5768603A Method and system for natural language translation 失效
公开(公告)号：US5768603A
公开(公告)日：1998-06-16
申请号：US459698
申请日：1995-06-02
申请人： Peter Fitzhugh Brown , John Cocke , Stephen Andrew Della Pietra , Vincent Joseph Della Pietra , Frederick Jelinek , Jennifer Ceil Lai , Robert Leroy Mercer
发明人： Peter Fitzhugh Brown , John Cocke , Stephen Andrew Della Pietra , Vincent Joseph Della Pietra , Frederick Jelinek , Jennifer Ceil Lai , Robert Leroy Mercer
IPC分类号： G10L15/14 , G06F17/27 , G06F17/28 , G10L15/00 , G06F17/20
CPC分类号： G06F17/2818 , G06F17/2755 , G06F17/2845 , G06F17/2872
摘要： The present invention is a system for translating text from a first source language into a second target language. The system assigns probabilities or scores to various target-language translations and then displays or makes otherwise available the highest scoring translations. The source text is first transduced into one or more intermediate structural representations. From these intermediate source structures a set of intermediate target-structure hypotheses is generated. These hypotheses are scored by two different models: a language model which assigns a probability or score to an intermediate target structure, and a translation model which assigns a probability or score to the event that an intermediate target structure is translated into an intermediate source structure. Scores from the translation model and language model are combined into a combined score for each intermediate target-structure hypothesis. Finally, a set of target-text hypotheses is produced by transducing the highest scoring target-structure hypotheses into portions of text in the target language. The system can either run in batch mode, in which case it translates source-language text into a target language without human assistance, or it can function as an aid to a human translator. When functioning as an aid to a human translator, the human may simply select from the various translation hypotheses provided by the system, or he may optionally provide hints or constraints on how to perform one or more of the stages of source transduction, hypothesis generation and target transduction.

5. 发明授权

US4748670A Apparatus and method for determining a likely word sequence from labels generated by an acoustic processor 失效
标题翻译：用于由声学处理器产生的标签确定可能的字序列的装置和方法
公开(公告)号：US4748670A
公开(公告)日：1988-05-31
申请号：US738911
申请日：1985-05-29
申请人： Lalit R. Bahl , Frederick Jelinek
发明人： Lalit R. Bahl , Frederick Jelinek
IPC分类号： G10L15/14 , G10L5/00
CPC分类号： G10L15/14
摘要： Continuous speech recognition is improved by use of a known vocabulary and context probabilities. First, the unknown utterance is analyzed as a sequence of phonemes, then each phoneme labelled to form a string of labels. The shortest label interval which is recognized as a word is assigned a storage stack where similar-sounding candidate words are stored. Multiple stack decoding, and liklihood envelope criteria for word path extension decisions, are further features of the system.
摘要翻译：通过使用已知的词汇和上下文概率来改善连续语音识别。首先，将未知话语分析为一系列音素，然后每个音素被标记以形成一串标签。被识别为字的最短标签间隔被分配存储相似的候选词的存储堆栈。多重堆栈解码和词路径扩展决策的可行包络标准是系统的进一步特征。

6. 发明授权

US5243149A Method and apparatus for improving the paper interface to computing systems 失效
标题翻译：用于改进计算系统的纸张界面的方法和装置
公开(公告)号：US5243149A
公开(公告)日：1993-09-07
申请号：US866681
申请日：1992-04-10
申请人： Liam D. Comerford , Hamed A. Ellozy , Frederick Jelinek , Stephen E. Levy , David Nahamoo
发明人： Liam D. Comerford , Hamed A. Ellozy , Frederick Jelinek , Stephen E. Levy , David Nahamoo
IPC分类号： G06F1/16 , G06F3/033
CPC分类号： G06F3/04883 , G06F1/1626 , G06F1/1656 , G06F1/1684 , G06F1/169 , G06F1/1696 , G06F3/033 , G06F2200/1632
摘要： The novel notepad of the invention provides a convenient interface into the capabilities of computer technology from paper based information. The notepad has a form factor similar to a clipboard wherein the board portion includes a digitizing tablet and the clip portion includes an optical scanner. A battery-powered embedded processor and associated peripherals provide for capturing and storing information in a variety of forms including at least scanning information, digitized stylus information and audio annotation. An important feature of the invention is the linking of these different forms of information via software so that while the information is readily available for efficient processing, it is also combinable so as to recreate the annotated document through conventional means.
摘要翻译：本发明的新颖的记事本提供了从基于纸的信息到计算机技术能力的便利的接口。记事本具有类似于剪贴板的形状因子，其中板部分包括数字化图形输入板，并且夹子部分包括光学扫描器。电池供电的嵌入式处理器和相关的外围设备提供捕获和存储各种形式的信息，包括至少扫描信息，数字化触笔信息和音频注释。本发明的一个重要特征是通过软件连接这些不同形式的信息，使得当信息容易获得有效处理时，它也是可组合的，以便通过常规方式重新创建注释的文档。

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