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

US07016829B2 Method and apparatus for unsupervised training of natural language processing units 失效
公开(公告)号：US07016829B2
公开(公告)日：2006-03-21
申请号：US09849833
申请日：2001-05-04
申请人： Eric D. Brill , Arul A. Menezes
发明人： Eric D. Brill , Arul A. Menezes
IPC分类号： G06F17/27 , G10L15/00
CPC分类号： G06F17/274
摘要： A method of training a natural language processing unit applies a candidate learning set to at least one component of the natural language unit. The natural language unit is then used to generate a meaning set from a first corpus. A second meaning set is generated from a second corpus using a second natural language unit and the two meaning sets are compared to each other to form a score for the candidate learning set. This score is used to determine whether to modify the natural language unit based on the candidate learning set.

2. 发明授权

US07233892B2 Method and apparatus for unsupervised training of natural language processing units 有权
标题翻译：自然语言处理单元无人训练的方法和装置
公开(公告)号：US07233892B2
公开(公告)日：2007-06-19
申请号：US11204213
申请日：2005-08-15
申请人： Eric D. Brill , Arul A. Menezes
发明人： Eric D. Brill , Arul A. Menezes
IPC分类号： G06F17/27 , G06F17/20 , G06F17/28
CPC分类号： G06F17/274
摘要： A method of training a natural language processing unit applies a candidate learning set to at least one component of the natural language unit. The natural language unit is then used to generate a meaning set from a first corpus. A second meaning set is generated from a second corpus using a second natural language unit and the two meaning sets are compared to each other to form a score for the candidate learning set. This score is used to determine whether to modify the natural language unit based on the candidate learning set.
摘要翻译：训练自然语言处理单元的方法将候选学习集合应用于自然语言单元的至少一个分量。然后，自然语言单元用于从第一语料库生成意义集。使用第二自然语言单元从第二语料库生成第二含义集合，并且将两个含义集合彼此进行比较以形成候选学习集合的分数。该分数用于确定是否基于候选学习集修改自然语言单元。

3. 发明授权

US08209162B2 Machine translation split between front end and back end processors 有权
标题翻译：机器翻译分为前端和后端处理器
公开(公告)号：US08209162B2
公开(公告)日：2012-06-26
申请号：US11414844
申请日：2006-05-01
申请人： Arul A. Menezes , Christopher B. Quirk , Richard F. Rashid , Robert C. Moore
发明人： Arul A. Menezes , Christopher B. Quirk , Richard F. Rashid , Robert C. Moore
IPC分类号： G06F17/28 , G06F17/21
CPC分类号： G06F17/289
摘要： A method of translation includes uploading a source text portion to a back end processor. The back end processor identifies a subset of translation knowledge associated with the source text portion. The back end processor downloads the subset to a front end processor. A translation engine runs on the front end processor. The translation engine generates a translation of the source text portion as a function of the subset.
摘要翻译：一种翻译方法包括将源文本部分上传到后端处理器。后端处理器识别与源文本部分相关联的翻译知识的子集。后端处理器将子集下载到前端处理器。翻译引擎在前端处理器上运行。翻译引擎生成作为子集的函数的源文本部分的翻译。

4. 发明授权

US5452353A Canonical telephone numbers 失效
标题翻译：规范电话号码
公开(公告)号：US5452353A
公开(公告)日：1995-09-19
申请号：US170999
申请日：1993-06-24
申请人： Arul A. Menezes
发明人： Arul A. Menezes
IPC分类号： H04M3/42 , H04M1/2745 , H04M1/27
CPC分类号： H04M1/274566 , Y10S379/912
摘要： A system and method using canonical telephone numbers which allows automatic calling with any location in the world independent of the caller's location. The caller canonical telephone number and a plurality of caller prefixes are stored within the system. A telephone directory stores a plurality of callee canonical telephone numbers for locations throughout the world. The caller selects a callee canonical telephone number from the telephone directory, and the system uses the callee canonical telephone number and the caller canonical telephone number to determine which digits of the callee canonical telephone number must be placed on the telephone line to complete the call. The system then adds the appropriate prefix for international, long distance, or local telephone calls. The telephone directory may be in the form of a software file that can be transferred to any telephone location throughout the world. The telephone directory may be directly installed at any caller location without alteration for the specific location. The user may use a keypad to enter new callee canonical telephone numbers into the telephone directory, or may manually enter a non-canonical callee telephone number.
摘要翻译：一种使用规范电话号码的系统和方法，允许在世界上与呼叫者位置无关的任何地点进行自动呼叫。呼叫者规范电话号码和多个呼叫者前缀存储在系统内。电话簿存储了世界各地的多个被叫方规范电话号码。来电者从电话簿中选择被叫方规范电话号码，系统使用被叫方规范电话号码和主叫方规范电话号码确定被叫方规则电话号码的哪些号码必须放在电话线路上以完成呼叫。然后，系统会为国际长途电话或本地电话添加适当的前缀。电话簿可以是可以传输到世界各地的任何电话位置的软件文件的形式。电话号码簿可以直接安装在任何呼叫者位置，而不会改变特定位置。用户可以使用小键盘将新的被呼叫规范电话号码输入到电话簿中，或者可以手动输入非规范被叫方电话号码。

5. 发明授权

US08150677B2 Machine translation using language order templates 有权
标题翻译：机器翻译使用语言订单模板
公开(公告)号：US08150677B2
公开(公告)日：2012-04-03
申请号：US12146531
申请日：2008-06-26
申请人： Arul A. Menezes , Christopher B. Quirk
发明人： Arul A. Menezes , Christopher B. Quirk
IPC分类号： G06F17/28
CPC分类号： G06F17/2872 , G06F17/2827
摘要： Many machine translation scenarios involve the generation of a language translation rule set based on parallel training corpuses (e.g., sentences in a first language and word-for-word translations into a second language.) However, the translation of a source corpus in a source language to a target corpus in a target language involves at least two aspects: selecting elements of the target language to match the elements of the source corpus, and ordering the target elements according to the semantic organization of the source corpus and the grammatic rules of the target language. The breadth of generalization of the translation rules derived from the training may be improved, while retaining contextual information, by formulating language order templates that specify orderings of small sets of target elements according to target element types. These language order templates may be represented with varying degrees of association with the alignment rules derived from the training in order to improve the scope of target elements to which the ordering rules and alignment rules may be applied.
摘要翻译：许多机器翻译方案涉及到基于平行训练语料库（例如，第一语言中的句子和逐字翻译成第二语言）的语言翻译规则集的生成。然而，源语料库在源中的翻译目标语言中的目标语料库的语言至少涉及两个方面：选择目标语言的元素以匹配源语料库的元素，并根据源语料库的语义组织和语法规则对目标元素进行排序目标语言。可以通过根据目标元素类型制定指定小组目标元素的排序的语言顺序模板，同时保留上下文信息，从而改进从训练中导出的翻译规则的广义化。这些语言顺序模板可以以与从训练导出的对准规则的不同程度的关联来表示，以便改进可以应用排序规则和对准规则的目标元素的范围。

6. 发明授权

US07698124B2 Machine translation system incorporating syntactic dependency treelets into a statistical framework 有权
标题翻译：机器翻译系统将句法依赖树结合到统计框架中
公开(公告)号：US07698124B2
公开(公告)日：2010-04-13
申请号：US11014503
申请日：2004-12-16
申请人： Arul A. Menezes , Christopher B. Quirk , Colin A. Cherry
发明人： Arul A. Menezes , Christopher B. Quirk , Colin A. Cherry
IPC分类号： G06F17/28
CPC分类号： G06F17/2818 , G06F17/28
摘要： In one embodiment of the present invention, a decoder receives a dependency tree as a source language input and accesses a set of statistical models that produce outputs combined in a log linear framework. The decoder also accesses a table of treelet translation pairs and returns a target dependency tree based on the source dependency tree, based on access to the table of treelet translation pairs, and based on the application of the statistical models.
摘要翻译：在本发明的一个实施例中，解码器接收依赖树作为源语言输入，并访问产生在对数线性框架中组合的输出的一组统计模型。解码器还访问树形图转换对的表，并基于对依赖树的转换对的访问，并且基于统计模型的应用，基于源依赖关系树返回目标依赖关系树。

7. 发明授权

US07577562B2 Extracting treelet translation pairs 有权
标题翻译：提取树皮翻译对
公开(公告)号：US07577562B2
公开(公告)日：2009-08-18
申请号：US11014492
申请日：2004-12-16
申请人： Arul A. Menezes , Christopher B. Quirk , Colin A. Cherry
发明人： Arul A. Menezes , Christopher B. Quirk , Colin A. Cherry
IPC分类号： G06F17/28
CPC分类号： G06F17/2818 , G06F17/28
摘要： In one embodiment of the present invention, a decoder receives a dependency tree as a source language input and accesses a set of statistical models that produce outputs combined in a log linear framework. The decoder also accesses a table of treelet translation pairs and returns a target dependency tree based on the source dependency tree, based on access to the table of treelet translation pairs, and based on the application of the statistical models.
摘要翻译：在本发明的一个实施例中，解码器接收依赖树作为源语言输入，并访问产生在对数线性框架中组合的输出的一组统计模型。解码器还访问树形图转换对的表，并基于对依赖树的转换对的访问，并且基于统计模型的应用，基于源依赖关系树返回目标依赖关系树。

8. 发明授权

US5475743A System and method for processing telephone numbers 失效
标题翻译：处理电话号码的系统和方法
公开(公告)号：US5475743A
公开(公告)日：1995-12-12
申请号：US148057
申请日：1993-11-05
申请人： Toby L. Nixon , Arul A. Menezes
发明人： Toby L. Nixon , Arul A. Menezes
IPC分类号： H04M3/42 , H04M1/2745 , H04M3/38
CPC分类号： H04M1/274566 , Y10S379/912
摘要： A system and method using canonical telephone numbers which allows automatic calling with any location in the world independent of the caller's location. The caller canonical telephone number and a plurality of caller prefixes are stored within the system. A telephone directory stores a plurality of callee canonical telephone numbers for locations throughout the world. The caller manually enters a callee telephone number or selects a callee telephone number from the telephone directory. The system determines if the callee telephone number is a canonical telephone number. The system expands non-canonical telephone numbers to canonical form using known telephone numbering rules for various countries. The system uses the callee canonical telephone number and the caller canonical telephone number to determine which digits of the callee canonical telephone number must be placed on the telephone line to complete the call. The system then adds the appropriate prefix for international, long distance, or local telephone calls to generate a final callee telephone number.
摘要翻译：一种使用规范电话号码的系统和方法，允许在世界上与呼叫者位置无关的任何地点进行自动呼叫。呼叫者规范电话号码和多个呼叫者前缀存储在系统内。电话簿存储了世界各地的多个被叫方规范电话号码。来电者手动输入被叫电话号码或从电话簿中选择被叫方电话号码。系统确定被叫电话号码是否是规范电话号码。该系统将非规范电话号码扩展到规范形式，使用各国已知的电话号码规则。该系统使用被叫方规范电话号码和呼叫方规范电话号码来确定被叫方规范电话号码的哪些数字必须放在电话线路上以完成呼叫。然后，系统会为国际长途或本地电话添加适当的前缀，以生成最后的被叫方电话号码。

9. 发明授权

US07593843B2 Statistical language model for logical form using transfer mappings 有权
标题翻译：统计语言模型的逻辑形式使用转移映射
公开(公告)号：US07593843B2
公开(公告)日：2009-09-22
申请号：US10813208
申请日：2004-03-30
申请人： Anthony Aue , Eric K. Ringger , Christopher B. Quirk , Arul A. Menezes , Robert C. Moore
发明人： Anthony Aue , Eric K. Ringger , Christopher B. Quirk , Arul A. Menezes , Robert C. Moore
IPC分类号： G06F17/28
CPC分类号： G06F17/2818 , G06F17/2881
摘要： A method of decoding an input semantic structure to generate an output semantic structure. A set of transfer mappings are provided. A score is calculated for at least one transfer mapping in the set of transfer mappings using a statistical model. At least one transfer mapping is selected based on the score and used to construct the output semantic structure.
摘要翻译：一种解码输入语义结构以生成输出语义结构的方法。提供一组传输映射。使用统计模型计算一组传输映射中的至少一个传输映射的分数。基于分数选择至少一个传输映射，并用于构建输出语义结构。

10. 发明授权

US07496496B2 System and method for machine learning a confidence metric for machine translation 有权
标题翻译：用于机器学习机器翻译的置信度量的系统和方法
公开(公告)号：US07496496B2
公开(公告)日：2009-02-24
申请号：US11725435
申请日：2007-03-19
申请人： Christopher B. Quirk , Arul A. Menezes , Stephen D. Richardson , Robert C. Moore
发明人： Christopher B. Quirk , Arul A. Menezes , Stephen D. Richardson , Robert C. Moore
IPC分类号： G06F17/28 , G06F17/20 , G10L11/00
CPC分类号： G06F17/28
摘要： A machine translation system is trained to generate confidence scores indicative of a quality of a translation result. A source string is translated with a machine translator to generate a target string. Features indicative of translation operations performed are extracted from the machine translator. A trusted entity-assigned translation score is obtained and is indicative of a trusted entity-assigned translation quality of the translated string. A relationship between a subset of the extracted features and the trusted entity-assigned translation score is identified.
摘要翻译：训练机器翻译系统以产生指示翻译结果的质量的置信度分数。使用机器翻译器翻译源字符串以生成目标字符串。从机器翻译器提取表示所执行的翻译操作的特征。获得受信任的实体分配的翻译分数，并且指示被翻译的字符串的受信任的实体分配的翻译质量。识别提取的特征的子集与可信实体分配的翻译分数之间的关系。

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