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

US07966173B2 System and method for diacritization of text 有权
标题翻译：文本变音的系统和方法
公开(公告)号：US07966173B2
公开(公告)日：2011-06-21
申请号：US11386626
申请日：2006-03-22
申请人： Ossama S. Emam , Ruhi Sarikaya , Imed Zitouni
发明人： Ossama S. Emam , Ruhi Sarikaya , Imed Zitouni
IPC分类号： G06F17/27
CPC分类号： G06F17/273 , G06F17/2863
摘要： A system and method for restoration of diacritics includes making classification decisions regarding an utterance in accordance with an aggregate of a plurality of information sources in a diacritization model for diacritic restoration. A best diacritic representation is determined for graphemes in the utterance based upon a best match with the diacritization model. A diacritically restored representation of the utterance is output.
摘要翻译：用于恢复变音符号的系统和方法包括根据用于变音符恢复的变音符号模型中的多个信息源的总计来做出关于话语的分类决定。基于与变异化模型的最佳匹配，确定话语中的字形的最佳偏差表示。输出语义的反义词恢复表示。

2. 发明申请

US20050276235A1 Packet loss concealment based on statistical n-gram predictive models for use in voice-over-IP speech transmission 有权
标题翻译：基于用于语音IP语音传输的统计n-gram预测模型的分组丢失隐藏
公开(公告)号：US20050276235A1
公开(公告)日：2005-12-15
申请号：US10856728
申请日：2004-05-28
申请人： Minkyu Lee , Qiru Zhou , Imed Zitouni
发明人： Minkyu Lee , Qiru Zhou , Imed Zitouni
IPC分类号： G10L19/00 , G10L19/04 , H04M7/00 , H04Q11/00
CPC分类号： G10L19/04 , G10L19/005 , H04L65/80 , H04Q2213/13034 , H04Q2213/13296 , H04Q2213/13389
摘要： A method for performing packet loss concealment of lost packets in Voice over IP (Internet Protocol) speech transmission. Statistical n-gram models are initially created with use of a training speech corpus, and then, packets lost during transmission are advantageously replaced based on these models. In particular, the existence of statistical patterns in successive voice over IP (VoIP) packets is advantageously exploited by first using conventional vector quantization (VQ) techniques to quantize the parameter data for each packet with use of a corresponding VQ index, and then determining statistical correlations between consecutive sequences of such VQ indices representative of the corresponding sequences of n packets. The statistic n-gram predictive models so created are then used to predict parameter data for use in representing lost data packets.
摘要翻译：一种用于在IP语音（因特网协议）语音传输中执行丢包隐藏丢失分组的方法。最初使用训练语音语料库创建统计n-gram模型，然后基于这些模型有利地替换传输期间丢失的分组。特别地，通过首先使用常规矢量量化（VQ）技术来利用相应的VQ索引对每个分组的参数数据进行量化，有利地利用连续IP语音（VoIP）分组中的统计模式的存在，然后确定统计这种VQ索引的连续序列之间的相关性表示n个分组的相应序列。然后，如此创建的统计量n-gram预测模型用于预测用于表示丢失数据分组的参数数据。

3. 发明授权

US08903707B2 Predicting pronouns of dropped pronoun style languages for natural language translation 有权
标题翻译：预测用于自然语言翻译的代词缩略语言代词
公开(公告)号：US08903707B2
公开(公告)日：2014-12-02
申请号：US13348995
申请日：2012-01-12
申请人： Bing Zhao , Imed Zitouni , Xiaoqiang Luo , Vittorio Castelli
发明人： Bing Zhao , Imed Zitouni , Xiaoqiang Luo , Vittorio Castelli
IPC分类号： G06F17/28
CPC分类号： G06F17/2827
摘要： A method, an apparatus and an article of manufacture for determining a dropped pronoun from a source language. The method includes collecting parallel sentences from a source and a target language, creating at least one word alignment between the parallel sentences in the source and the target language, mapping at least one pronoun from the target language sentence onto the source language sentence, computing at least one feature from the mapping, wherein the at least one feature is extracted from both the source language and the at least one pronoun projected from the target language, and using the at least one feature to train a classifier to predict position and spelling of at least one pronoun in the target language when the at least one pronoun is dropped in the source language.
摘要翻译：一种用于从源语言确定掉落代词的方法，装置和制品。该方法包括从源和目标语言收集并行句子，在源和目标语言中的并行句子之间创建至少一个单词对齐，将来自目标语言句子的至少一个代词映射到源语言句子上，计算所述映射中的至少一个特征，其中从所述源语言和从所述目标语言投射的所述至少一个代词中提取所述至少一个特征，并且使用所述至少一个特征来训练分类器来预测位置和拼写的位置和拼写当至少一个代词在源语言中被删除时，目标语言中至少有一个代词。

4. 发明申请

US20090299925A1 Automatic Detection of Undesirable Users of an Online Communication Resource Based on Content Analytics 有权
标题翻译：基于内容分析的在线通信资源的不良用户的自动检测
公开(公告)号：US20090299925A1
公开(公告)日：2009-12-03
申请号：US12129803
申请日：2008-05-30
申请人： Ganesh N. Ramaswamy , Imed Zitouni
发明人： Ganesh N. Ramaswamy , Imed Zitouni
IPC分类号： G06F15/18
CPC分类号： G06F21/552 , G06F21/316
摘要： An exemplary processor-implemented method of determining whether a user of an online communication resource is an undesirable user includes the steps of building at least one model based on at least one feature of a feature set using at least one machine learning technique; and classifying the user by comparing at least one feature of the feature set that is associated with the user to the at least one model, a determination as to whether the user is an undesirable user being based at least in part on the classification of the user.
摘要翻译：一种用于确定在线通信资源的用户是否是不期望的用户的示例性处理器实现的方法包括以下步骤：使用至少一个机器学习技术基于特征集的至少一个特征构建至少一个模型; 以及通过将与所述用户相关联的所述特征集的至少一个特征与所述至少一个模型进行比较来对所述用户进行分类，至少部分地基于所述用户的分类来确定所述用户是否是不期望的用户是否是不期望的用户。

5. 发明授权

US08527262B2 Systems and methods for automatic semantic role labeling of high morphological text for natural language processing applications 有权
标题翻译：用于自然语言处理应用的高形态文本的自动语义角色标记的系统和方法
公开(公告)号：US08527262B2
公开(公告)日：2013-09-03
申请号：US11767104
申请日：2007-06-22
申请人： Nandakishore Kambhatla , Imed Zitouni
发明人： Nandakishore Kambhatla , Imed Zitouni
IPC分类号： G06F17/28
CPC分类号： G06F17/2785 , G06F17/277
摘要： Systems and methods are provided for automated semantic role labeling for languages having complex morphology. In one aspect, a method for processing natural language text includes receiving as input a natural language text sentence comprising a sequence of white-space delimited words including inflicted words that are formed of morphemes including a stem and one or more affixes, identifying a target verb as a stem of an inflicted word in the text sentence, grouping morphemes from one or more inflicted words with the same syntactic role into constituents, and predicting a semantic role of a constituent for the target verb.
摘要翻译：为具有复杂形态的语言提供了自动语义角色标签的系统和方法。在一个方面，一种用于处理自然语言文本的方法包括接收包括一系列白空格限定词的自然语言文本句子作为输入，所述单词包括由包括词干和一个或多个词缀的语素形成的受影响词，标识目标动词作为文本句中的一个词语的句子，将来自一个或多个具有相同句法角色的词语的语素分成三方成员，并且将目标动词的成分的语义角色预测出来。

6. 发明申请

US20130185049A1 Predicting Pronouns for Pro-Drop Style Languages for Natural Language Translation 有权
标题翻译：预测自然语言翻译中Pro-Drop风格语言的代词
公开(公告)号：US20130185049A1
公开(公告)日：2013-07-18
申请号：US13348995
申请日：2012-01-12
申请人： Bing Zhao , Imed Zitouni , Xiaoqiang Luo , Vittorio Castelli
发明人： Bing Zhao , Imed Zitouni , Xiaoqiang Luo , Vittorio Castelli
IPC分类号： G06F17/28 , G06F17/27
CPC分类号： G06F17/2827
摘要： A method, an apparatus and an article of manufacture for determining a dropped pronoun from a source language. The method includes collecting parallel sentences from a source and a target language, creating at least one word alignment between the parallel sentences in the source and the target language, mapping at least one pronoun from the target language sentence onto the source language sentence, computing at least one feature from the mapping, wherein the at least one feature is extracted from both the source language and the at least one pronoun projected from the target language, and using the at least one feature to train a classifier to predict position and spelling of at least one pronoun in the target language when the at least one pronoun is dropped in the source language.
摘要翻译：一种用于从源语言确定掉落代词的方法，装置和制品。该方法包括从源和目标语言收集并行句子，在源和目标语言中的并行句子之间创建至少一个单词对齐，将来自目标语言句子的至少一个代词映射到源语言句子上，计算所述映射中的至少一个特征，其中从所述源语言和从所述目标语言投射的所述至少一个代词中提取所述至少一个特征，并且使用所述至少一个特征来训练分类器来预测位置和拼写的位置和拼写当至少一个代词在源语言中被删除时，目标语言中至少有一个代词。

7. 发明授权

US07701886B2 Packet loss concealment based on statistical n-gram predictive models for use in voice-over-IP speech transmission 有权
标题翻译：基于用于语音IP语音传输的统计n-gram预测模型的分组丢失隐藏
公开(公告)号：US07701886B2
公开(公告)日：2010-04-20
申请号：US10856728
申请日：2004-05-28
申请人： Minkyu Lee , Qiru Zhou , Imed Zitouni
发明人： Minkyu Lee , Qiru Zhou , Imed Zitouni
IPC分类号： H04Q11/00
CPC分类号： G10L19/04 , G10L19/005 , H04L65/80 , H04Q2213/13034 , H04Q2213/13296 , H04Q2213/13389
摘要： A method for performing packet loss concealment of lost packets in Voice over IP (Internet Protocol) speech transmission. Statistical n-gram models are initially created with use of a training speech corpus, and then, packets lost during transmission are advantageously replaced based on these models. In particular, the existence of statistical patterns in successive voice over IP (VoIP) packets is advantageously exploited by first using conventional vector quantization (VQ) techniques to quantize the parameter data for each packet with use of a corresponding VQ index, and then determining statistical correlations between consecutive sequences of such VQ indices representative of the corresponding sequences of n packets. The statistic n-gram predictive models so created are then used to predict parameter data for use in representing lost data packets.
摘要翻译：一种用于在IP语音（因特网协议）语音传输中执行丢包隐藏丢失分组的方法。最初使用训练语音语料库创建统计n-gram模型，然后基于这些模型有利地替换传输期间丢失的分组。特别地，通过首先使用常规矢量量化（VQ）技术来利用相应的VQ索引对每个分组的参数数据进行量化，有利地利用连续IP语音（VoIP）分组中的统计模式的存在，然后确定统计这种VQ索引的连续序列之间的相关性表示n个分组的相应序列。然后，如此创建的统计量n-gram预测模型用于预测用于表示丢失数据分组的参数数据。

8. 发明授权

US08412645B2 Automatic detection of undesirable users of an online communication resource based on content analytics 有权
标题翻译：基于内容分析自动检测在线通信资源的不良用户
公开(公告)号：US08412645B2
公开(公告)日：2013-04-02
申请号：US12129803
申请日：2008-05-30
申请人： Ganesh N. Ramaswamy , Imed Zitouni
发明人： Ganesh N. Ramaswamy , Imed Zitouni
IPC分类号： G06N5/00
CPC分类号： G06F21/552 , G06F21/316
摘要： An exemplary processor-implemented method of determining whether a user of an online communication resource is an undesirable user includes the steps of building at least one model based on at least one feature of a feature set using at least one machine learning technique; and classifying the user by comparing at least one feature of the feature set that is associated with the user to the at least one model, a determination as to whether the user is an undesirable user being based at least in part on the classification of the user.
摘要翻译：一种用于确定在线通信资源的用户是否是不期望的用户的示例性处理器实现的方法包括以下步骤：使用至少一个机器学习技术基于特征集的至少一个特征构建至少一个模型; 以及通过将与所述用户相关联的所述特征集的至少一个特征与所述至少一个模型进行比较来对所述用户进行分类，至少部分地基于所述用户的分类来确定所述用户是否是不期望的用户是否是不期望的用户。

9. 发明申请

US20080319735A1 SYSTEMS AND METHODS FOR AUTOMATIC SEMANTIC ROLE LABELING OF HIGH MORPHOLOGICAL TEXT FOR NATURAL LANGUAGE PROCESSING APPLICATIONS 有权
标题翻译：用于自然语言处理应用的高自然语言文本的自动语言角色标签的系统和方法
公开(公告)号：US20080319735A1
公开(公告)日：2008-12-25
申请号：US11767104
申请日：2007-06-22
申请人： Nandakishore Kambhatla , Imed Zitouni
发明人： Nandakishore Kambhatla , Imed Zitouni
IPC分类号： G06F17/27
CPC分类号： G06F17/2785 , G06F17/277
摘要： Systems and methods are provided for automated semantic role labeling for languages having complex morphology. In one aspect, a method for processing natural language text includes receiving as input a natural language text sentence comprising a sequence of white-space delimited words including inflicted words that are formed of morphemes including a stem and one or more affixes, identifying a target verb as a stem of an inflicted word in the text sentence, grouping morphemes from one or more inflicted words with the same syntactic role into constituents, and predicting a semantic role of a constituent for the target verb.
摘要翻译：为具有复杂形态的语言提供了自动语义角色标签的系统和方法。在一个方面，一种用于处理自然语言文本的方法包括接收包括一系列白空格限定词的自然语言文本句子作为输入，所述单词包括由包括词干和一个或多个词缀的语素形成的受影响词，标识目标动词作为文本句中的一个词语的句子，将来自一个或多个具有相同句法角色的词语的语素分成三方成员，并且将目标动词的成分的语义角色预测出来。

10. 发明申请

US20080270115A1 SYSTEM AND METHOD FOR DIACRITIZATION OF TEXT 审中-公开
标题翻译：文本分类的系统和方法
公开(公告)号：US20080270115A1
公开(公告)日：2008-10-30
申请号：US12132072
申请日：2008-06-03
申请人： Ossama S. Emam , Ruhi Sarikaya , Imed Zitouni
发明人： Ossama S. Emam , Ruhi Sarikaya , Imed Zitouni
IPC分类号： G06F17/20
CPC分类号： G06F17/273 , G06F17/2863
摘要： A system and method for restoration of diacritics includes making classification decisions regarding an utterance in accordance with an aggregate of a plurality of information sources in a diacritization model for diacritic restoration. A best diacritic representation is determined for graphemes in the utterance based upon a best match with the diacritization model. A diacritically restored representation of the utterance is output.
摘要翻译：用于恢复变音符号的系统和方法包括根据用于变音符恢复的变音符号模型中的多个信息源的总计来做出关于话语的分类决定。基于与变异化模型的最佳匹配，确定话语中的字形的最佳偏差表示。输出语义的反义词恢复表示。

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