公开(公告)号：US20100076746A1

公开(公告)日：2010-03-25

申请号：US12238207

申请日：2008-09-25

申请人： Takako Aikawa ,  Achim Ruopp

发明人： Takako Aikawa ,  Achim Ruopp

IPC分类号： G06F17/28

CPC分类号： G06F17/2818 ,  G06F17/2775 ,  G06F17/2827 ,  G06F17/289

摘要： A computerized system for performing statistical machine translation with a phrasal decoder is provided. The system may include a phrasal decoder trained prior to run-time on a monolingual parallel corpus, the monolingual parallel corpus including a machine translation output of source language documents of a bilingual parallel corpus and a corresponding target human translation output of the source language documents, to thereby learn mappings between the machine translation output and the target human translation output. The system may further include a statistical machine translation engine configured to receive a translation input and to produce a raw machine translation output, at run-time. The phrasal decoder may be configured to process the raw machine translation output, and to produce a corrected translation output based on the learned mappings for display on a display associated with the system.

摘要翻译： 提供了一种用于使用短语解码器执行统计机器翻译的计算机化系统。 该系统可以包括在单语平行语料库之前运行时训练的短语解码器，单语平行语料库包括双语平行语料库的源语言文档的机器翻译输出和源语言文档的相应目标人类翻译输出， 从而学习机器翻译输出和目标人类翻译输出之间的映射。 该系统可以进一步包括统计机器翻译引擎，其被配置为在运行时接收翻译输入并产生原始机器翻译输出。 短语解码器可以被配置为处理原始机器翻译输出，并且基于所学习的映射来产生用于在与系统相关联的显示器上显示的校正的转换输出。

公开(公告)号：US20090063126A1

公开(公告)日：2009-03-05

申请号：US11897197

申请日：2007-08-29

申请人： Masaki Itagaki ,  Takako Aikawa ,  Xiaodong He

发明人： Masaki Itagaki ,  Takako Aikawa ,  Xiaodong He

IPC分类号： G06F17/28

CPC分类号： G06F17/2818

摘要： A method of determining the consistency of training data for a machine translation system is disclosed. The method includes receiving a signal indicative of a source language corpus and a target language corpus. A textual string is extracted from the source language corpus. The textual string is aligned with the target language corpus to identify a translation for the textual string from the target language corpus. A consistency index is calculated based on a relationship between the textual string from the source language corpus and the translation. An indication of the consistency index is stored on a tangible medium.

摘要翻译： 公开了一种确定机器翻译系统的训练数据的一致性的方法。 该方法包括接收指示源语言语料库和目标语言语料库的信号。 从源语言语料库中提取文本字符串。 文本字符串与目标语言语料库对齐，以从目标语言语料库中标识文本字符串的翻译。 基于源语言语料库的文本字符串与翻译之间的关系计算一致性索引。 一致性指数的指示存储在有形介质上。

公开(公告)号：US08548791B2

公开(公告)日：2013-10-01

申请号：US11897197

申请日：2007-08-29

申请人： Masaki Itagaki ,  Takako Aikawa ,  Xiaodong He

发明人： Masaki Itagaki ,  Takako Aikawa ,  Xiaodong He

IPC分类号： G06F17/28 ,  G06F17/20

CPC分类号： G06F17/2818

摘要： A method of determining the consistency of training data for a machine translation system is disclosed. The method includes receiving a signal indicative of a source language corpus and a target language corpus. A textual string is extracted from the source language corpus. The textual string is aligned with the target language corpus to identify a translation for the textual string from the target language corpus. A consistency index is calculated based on a relationship between the textual string from the source language corpus and the translation. An indication of the consistency index is stored on a tangible medium.

公开(公告)号：US20060217979A1

公开(公告)日：2006-09-28

申请号：US11086880

申请日：2005-03-22

申请人： Michel Pahud ,  Takako Aikawa ,  Lee Schwartz

发明人： Michel Pahud ,  Takako Aikawa ,  Lee Schwartz

IPC分类号： G10L15/18

CPC分类号： H04N21/44012 ,  G06T13/00 ,  H04N21/23412

摘要： The subject invention provides a unique system and method that facilitates integrating natural language input and graphics in a cooperative manner. In particular, as natural language input is entered by a user, an illustrated or animated scene can be generated to correspond to such input. The natural language input can be in sentence form. Upon detection of an end-of-sentence indicator, the input can be processed using NLP techniques and the images or templates representing at least one of the actor, action, background and/or object specified in the input can be selected and rendered. Thus, the user can nearly immediately visualize an illustration of his/her input. The input can be typed, written, or spoken—whereby speech recognition can be employed to convert the speech to text. New graphics can be created as well to allow the customization and expansion of the invention according to the user's preferences.

公开(公告)号：US20100082324A1

公开(公告)日：2010-04-01

申请号：US12241123

申请日：2008-09-30

申请人： Masaki Itagaki ,  Takako Aikawa

发明人： Masaki Itagaki ,  Takako Aikawa

IPC分类号： G06F17/28

CPC分类号： G06F17/2836

摘要： A system described herein includes a receiver component that receives an output translation from a machine translation system, wherein the output translation is in a target language and is based at least in part upon an input to the machine translation system in a source language, and wherein the input to the machine translation system includes a first term in the source language and the output translation includes a second term in the target language that corresponds to the first term. The system additionally includes a replacer component in communication with the receiver component that accesses a dictionary of term correspondences, wherein the dictionary of term correspondences includes an indication that the input first term in the source language is desirably translated to a third term in the target language, and wherein the replacer component is configured to automatically replace the second term with the third term to modify the output translation.

摘要翻译： 本文描述的系统包括从机器翻译系统接收输出转换的接收器组件，其中输出转换是目标语言，并且至少部分地基于源语言对机器翻译系统的输入，并且其中 机器翻译系统的输入包括源语言中的第一项，并且输出翻译包括对应于第一项的目标语言中的第二项。 该系统还包括与接收器组件通信的替换器组件，其访问术语对应字典，其中术语对应字典包括将源语言中的输入第一项期望地转换为目标语言中的第三项的指示 ，并且其中所述替换器组件被配置为用第三项来自动替换所述第二项以修改所述输出转换。

公开(公告)号：US09176952B2

公开(公告)日：2015-11-03

申请号：US12238207

申请日：2008-09-25

申请人： Takako Aikawa ,  Achim Ruopp

发明人： Takako Aikawa ,  Achim Ruopp

IPC分类号： G06F17/28 ,  G06F17/27

CPC分类号： G06F17/2818 ,  G06F17/2775 ,  G06F17/2827 ,  G06F17/289

摘要： A computerized system for performing statistical machine translation with a phrasal decoder is provided. The system may include a phrasal decoder trained prior to run-time on a monolingual parallel corpus, the monolingual parallel corpus including a machine translation output of source language documents of a bilingual parallel corpus and a corresponding target human translation output of the source language documents, to thereby learn mappings between the machine translation output and the target human translation output. The system may further include a statistical machine translation engine configured to receive a translation input and to produce a raw machine translation output, at run-time. The phrasal decoder may be configured to process the raw machine translation output, and to produce a corrected translation output based on the learned mappings for display on a display associated with the system.

摘要翻译： 提供了一种用于使用短语解码器执行统计机器翻译的计算机化系统。 该系统可以包括在单语平行语料库之前运行时训练的短语解码器，单语平行语料库包括双语平行语料库的源语言文档的机器翻译输出和源语言文档的相应目标人类翻译输出， 从而学习机器翻译输出和目标人类翻译输出之间的映射。 该系统可以进一步包括统计机器翻译引擎，其被配置为在运行时接收翻译输入并产生原始机器翻译输出。 短语解码器可以被配置为处理原始机器翻译输出，并且基于所学习的映射来产生用于在与系统相关联的显示器上显示的校正的转换输出。

公开(公告)号：US20110252316A1

公开(公告)日：2011-10-13

申请号：US12758060

申请日：2010-04-12

申请人： Michel Pahud ,  Takako Aikawa ,  Andrew D. Wilson ,  Hrvoje Benko ,  Sauleh Eetemadi ,  Anand M. Chakravarty

发明人： Michel Pahud ,  Takako Aikawa ,  Andrew D. Wilson ,  Hrvoje Benko ,  Sauleh Eetemadi ,  Anand M. Chakravarty

IPC分类号： G06F17/28 ,  G06F3/01 ,  G06F17/24 ,  G06F3/048

CPC分类号： G06F17/289

摘要： A system described herein includes an acquirer component that acquires an electronic document that comprises text in a first language, wherein the acquirer component acquires the electronic document based at least in part upon a physical object comprising the text contacting or becoming proximate to the interactive display of the surface computing device. The system also includes a language selector component that receives an indication of a second language from a user of the surface computing device and selects the second language. A translator component translates the text in the electronic document from the first language to the second language, and a formatter component formats the electronic document for display to the user on the interactive display of the surface computing device, wherein the electronic document comprises the text in the second language.

摘要翻译： 本文描述的系统包括获取包含第一语言的文本的电子文档的获取器组件，其中所述获取器组件至少部分地基于包括接触或变得接近于交互式显示的文本的物理对象获取电子文档 表面计算设备。 该系统还包括语言选择器组件，其从表面计算设备的用户接收第二语言的指示并选择第二语言。 翻译器组件将电子文档中的文本从第一语言翻译成第二语言，并且格式化器组件在表面计算设备的交互式显示器上将用于显示的电子文档格式化为用户，其中电子文档包括文本 第二语言

公开(公告)号：US07512537B2

公开(公告)日：2009-03-31

申请号：US11086880

申请日：2005-03-22

申请人： Michel Pahud ,  Takako Aikawa ,  Lee A. Schwartz

发明人： Michel Pahud ,  Takako Aikawa ,  Lee A. Schwartz

IPC分类号： G10L21/00 ,  G10L15/00 ,  G06F17/27 ,  G06T13/00

CPC分类号： H04N21/44012 ,  G06T13/00 ,  H04N21/23412

摘要： The subject invention provides a unique system and method that facilitates integrating natural language input and graphics in a cooperative manner. In particular, as natural language input is entered by a user, an illustrated or animated scene can be generated to correspond to such input. The natural language input can be in sentence form. Upon detection of an end-of-sentence indicator, the input can be processed using NLP techniques and the images or templates representing at least one of the actor, action, background and/or object specified in the input can be selected and rendered. Thus, the user can nearly immediately visualize an illustration of his/her input. The input can be typed, written, or spoken—whereby speech recognition can be employed to convert the speech to text. New graphics can be created as well to allow the customization and expansion of the invention according to the user's preferences.

摘要翻译： 本发明提供了一种有助于以合作的方式整合自然语言输入和图形的独特系统和方法。 特别地，当用户输入自然语言输入时，可以产生图示或动画场景以对应于这样的输入。 自然语言输入可以是句子形式。 在检测到句末结束指示符之后，可以使用NLP技术来处理输入，并且可以选择和呈现表示输入中指定的行为者，动作，背景和/或对象中的至少一个的图像或模板。 因此，用户几乎可以立即显示他/她的输入的图示。 输入可以被输入，写入或者说，从而可以使用语音识别来将语音转换为文本。 还可以创建新的图形，以便根据用户的偏好允许本发明的定制和扩展。