公开(公告)号：US20140303955A1

公开(公告)日：2014-10-09

申请号：US13820199

申请日：2011-05-25

申请人： Sang-Bum Kim ,  Chang Hao Yin ,  Young Sook Hwang ,  Hae Chang Rim ,  Hyoung Gyu Lee

发明人： Sang-Bum Kim ,  Chang Hao Yin ,  Young Sook Hwang ,  Hae Chang Rim ,  Hyoung Gyu Lee

IPC分类号： G06F17/28

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

摘要： The present disclosure relates to an apparatus and a method for recognizing an idiomatic expression using phrase alignment of a bilingual parallel corpus, and more particularly, to an apparatus and a method for recognizing an idiomatic expression using phrase alignment of a parallel corpus which extract a candidate idiomatic expression using phrase alignment information of a bilingual parallel corpus and measure an idiomatic expression index for every extracted candidate idiomatic expression to recognize the candidate idiomatic expression as an idiomatic expression to resolve errors in measuring a translational entropy of a word and extracting a representative translated word of the word and improve the accuracy of the idiomatic expression recognition.

摘要翻译： 本公开涉及一种使用双语平行语料库的短语对齐来识别习语表达的装置和方法，更具体地，涉及一种使用提取候选者的平行语料库的短语对齐来识别惯用语言的装置和方法 使用双语平行语料库的短语对齐信息的习语表达，并测量每个提取的候选习语表达式的惯用表达式，以将候选习语表达式识别为惯用语言，以解决测量单词的翻译熵和提取代表性翻译单词时的错误 的字，提高习语表达式的准确性。

公开(公告)号：US10198437B2

公开(公告)日：2019-02-05

申请号：US13883758

申请日：2011-07-20

申请人： Young Sook Hwang ,  Sang-Bum Kim ,  Chang Hao Yin ,  Yeon Su Lee ,  Seong Wook Lee ,  Hae Chang Rim

发明人： Young Sook Hwang ,  Sang-Bum Kim ,  Chang Hao Yin ,  Yeon Su Lee ,  Seong Wook Lee ,  Hae Chang Rim

IPC分类号： G06F17/28

摘要： The present invention relates to statistical machine translation, and provides a machine translation device and a machine translation method that acquire a creation probability for a target language from a single corpus while extracting respective conversion probabilities by extracting syntax conversion knowledge and word translation knowledge from a parallel corpus, model a weighted translation model by allowing each of the conversion knowledge and each of the probabilities to learn using a translation model learning device, and generate a target sentence through decoding processes of a syntax converter and a word translator by applying the translation model to a source sentence input in real time, thereby resolving disadvantages of the existing phrase-based SMT and syntax-based SMT and combining advantages thereof.

公开(公告)号：US20130226556A1

公开(公告)日：2013-08-29

申请号：US13883758

申请日：2011-07-20

申请人： Young Sook Hwang ,  Sang-Bum Kim ,  Chang Hao Yin ,  Yeon Su Lee ,  Seong Wook Lee ,  Hae Chang Rim

发明人： Young Sook Hwang ,  Sang-Bum Kim ,  Chang Hao Yin ,  Yeon Su Lee ,  Seong Wook Lee ,  Hae Chang Rim

IPC分类号： G06F17/28

CPC分类号： G06F17/289 ,  G06F17/2818 ,  G06F17/2872

摘要： The present invention relates to statistical machine translation, and provides a machine translation device and a machine translation method that acquire a creation probability for a target language from a single corpus while extracting respective conversion probabilities by extracting syntax conversion knowledge and word translation knowledge from a parallel corpus, model a weighted translation model by allowing each of the conversion knowledge and each of the probabilities to learn using a translation model learning device, and generate a target sentence through decoding processes of a syntax converter and a word translator by applying the translation model to a source sentence input in real time, thereby resolving disadvantages of the existing phrase-based SMT and syntax-based SMT and combining advantages thereof.

摘要翻译： 本发明涉及统计机器翻译，并且提供一种机器翻译装置和机器翻译方法，其从单个语料库获取目标语言的创建概率，同时通过从并行提取语法转换知识和文字翻译知识来提取相应的转换概率 语料库，通过允许每个转换知识和每个概率学习使用翻译模型学习装置来建模加权翻译模型，并且通过将翻译模型应用于语法转换器和单词翻译器的解码处理来生成目标句子 源语句实时输入，从而解决现有的基于短语的SMT和基于语法的SMT的缺点，并结合其优点。

公开(公告)号：US20140012564A1

公开(公告)日：2014-01-09

申请号：US13878082

申请日：2011-07-08

申请人： Young Sook Hwang ,  Sang-Bum Kim ,  Chang Hao Yin ,  Hae Chang Rim ,  Joo Young Lee

发明人： Young Sook Hwang ,  Sang-Bum Kim ,  Chang Hao Yin ,  Hae Chang Rim ,  Joo Young Lee

IPC分类号： G06F17/28

CPC分类号： G06F17/28 ,  G06F17/271 ,  G06F17/2775 ,  G06F17/2818 ,  G06F17/2827

摘要： Disclosed all an apparatus and a method for constructing a verb phrase translation pattern using a bilingual parallel corpus which recognizes a predicate and an argument using a syntax analysis result and a word alignment result of a source sentence from a plurality of bilingual parallel corpus, extracts a translation pattern candidate and an occurrence frequency using the recognized predicate and argument, and then generates a basic verb phrase translation pattern by verifying the translation pattern candidate, and generalizes the generated basic verb phrase translation pattern to generate a general verb phrase pattern so as to be applied to various language pairs and minimize an error in the verb phrase translation pattern and determine an appropriate generalization level using a co-occurrence frequency of a predicate and an argument of the verb phrase translation pattern and a translation probability of the predicate.

摘要翻译： 公开了使用双语平行语料库构建动词短语翻译模式的所有装置和方法，其使用来自多个双语平行语料库的语言分析结果和源语句的词对齐结果识别谓词和参数，提取 翻译模式候选者和使用识别的谓词和参数的出现频率，然后通过验证翻译模式候选来生成基本的动词短语翻译模式，并且将所生成的基本动词短语翻译模式概括为一般的动词短语模式，以便成为 应用于各种语言对，并使动词短语翻译模式中的错误最小化，并使用动词短语翻译模式的谓词和参数的共现频率以及谓词的翻译概率来确定适当的泛化级别。

公开(公告)号：US08818792B2

公开(公告)日：2014-08-26

申请号：US13878082

申请日：2011-07-08

申请人： Young Sook Hwang ,  Sang-Bum Kim ,  Chang Hao Yin ,  Hae Chang Rim ,  Joo Young Lee

发明人： Young Sook Hwang ,  Sang-Bum Kim ,  Chang Hao Yin ,  Hae Chang Rim ,  Joo Young Lee

IPC分类号： G06F17/28

CPC分类号： G06F17/28 ,  G06F17/271 ,  G06F17/2775 ,  G06F17/2818 ,  G06F17/2827

摘要： An apparatus and a method for constructing a verb phrase translation pattern using a bilingual parallel corpus. Each of the apparatus or method recognizes a predicate and an argument using a syntax analysis result and a word alignment result of a source sentence from a plurality of bilingual parallel corpus, extracts a translation pattern candidate and an occurrence frequency using the recognized predicate and argument, and then generates a basic verb phrase translation pattern by verifying the translation pattern candidate, and generalizes the generated basic verb phrase translation pattern to generate a general verb phrase pattern so as to be applied to various language pairs and minimize an error in the verb phrase translation pattern and determine an appropriate generalization level using a co-occurrence frequency of a predicate and an argument of the verb phrase translation pattern and a translation probability of the predicate.

摘要翻译： 一种使用双语平行语料库构建动词短语翻译模式的装置和方法。 所述装置或方法中的每一个使用语法分析结果和来自多个双语平行语料库的源语句的单词对齐结果识别谓词和参数，使用所识别的谓词和参数提取翻译模式候选和出现频率， 然后通过验证翻译模式候选来生成基本的动词短语翻译模式，并且将所生成的基本动词短语翻译模式概括为生成一般动词短语模式，以便应用于各种语言对，并使动词短语翻译中的错误最小化 使用动词短语翻译模式的谓词和参数的共现频率以及谓词的翻译概率来确定适当的泛化级别。

公开(公告)号：US20130132064A1

公开(公告)日：2013-05-23

申请号：US13813463

申请日：2011-05-25

申请人： Young Sook Hwang ,  Sang-Bum Kim ,  Chang Hao Yin ,  Xinyan Xiao ,  Yang Liu ,  Qun Liu ,  Shouxun Lin

发明人： Young Sook Hwang ,  Sang-Bum Kim ,  Chang Hao Yin ,  Xinyan Xiao ,  Yang Liu ,  Qun Liu ,  Shouxun Lin

IPC分类号： G06F17/28

CPC分类号： G06F17/28 ,  G06F17/2818 ,  G06F17/2863

摘要： Disclosed are a joint decoding apparatus and a joint decoding method that joins a tokenization process and a translation process. More particularly, the present disclosure can generate all available candidate tokens, reduce translation errors, and obtain an optimal translation result by jointly conducting a decoding by simultaneously conducting the tokenization process and the translation process for an input character sequence while decoding.

摘要翻译： 公开了一种联合解码装置和联合解码方法，其连接令牌化处理和翻译处理。 更具体地，本公开可以通过在解码时同时进行令牌化处理和输入字符序列的转换处理来共同进行解码来生成所有可用的候选令牌，减少翻译错误，并获得最佳翻译结果。

公开(公告)号：US08543376B2

公开(公告)日：2013-09-24

申请号：US13813463

申请日：2011-05-25

申请人： Young Sook Hwang ,  Sang-Bum Kim ,  Chang Hao Yin ,  Xinyan Xiao ,  Yang Liu ,  Qun Liu ,  Shouxun Lin

发明人： Young Sook Hwang ,  Sang-Bum Kim ,  Chang Hao Yin ,  Xinyan Xiao ,  Yang Liu ,  Qun Liu ,  Shouxun Lin

IPC分类号： G06F17/28

CPC分类号： G06F17/28 ,  G06F17/2818 ,  G06F17/2863

摘要： Disclosed are a joint decoding apparatus and a joint decoding method that joins a tokenization process and a translation process. More particularly, the present disclosure can generate all available candidate tokens, reduce translation errors, and obtain an optimal translation result by jointly conducting a decoding by simultaneously conducting the tokenization process and the translation process for an input character sequence while decoding.

摘要翻译： 公开了一种联合解码装置和联合解码方法，其连接令牌化处理和翻译处理。 更具体地，本公开可以通过在解码时同时进行令牌化处理和输入字符序列的转换处理来共同进行解码来生成所有可用的候选令牌，减少翻译错误，并获得最佳翻译结果。

公开(公告)号：US20130158975A1

公开(公告)日：2013-06-20

申请号：US13818137

申请日：2011-05-31

申请人： Young Sook Hwang ,  Sang-Bum Kim ,  Shouxun Lin ,  Zhaopeng Tu ,  Yang Liu ,  Qun Liu ,  Chang Hao Yin

发明人： Young Sook Hwang ,  Sang-Bum Kim ,  Shouxun Lin ,  Zhaopeng Tu ,  Yang Liu ,  Qun Liu ,  Chang Hao Yin

IPC分类号： G06F17/28

CPC分类号： G06F17/2872 ,  G06F17/271 ,  G06F17/2818

摘要： The present invention relates to the use of a plurality of dependency trees in tree-based statistical machine translation and proposes a dependency forest to effectively process the plurality of dependency trees. The present invention can improve a translation capability by generating a translation rule and a dependency language model by using the dependency forest and applying the generated translation rule and dependency language model when a source language text is converted to a target language text.

摘要翻译： 本发明涉及在基于树的统计机器翻译中使用多个依赖关系树，并且提出依赖林以有效地处理多个依赖关系树。 本发明可以通过在源语言文本被转换为目标语言文本时通过使用依赖性林并应用生成的翻译规则和依赖语言模型来生成翻译规则和依赖语言模型来提高翻译能力。

公开(公告)号：US20130117010A1

公开(公告)日：2013-05-09

申请号：US13809835

申请日：2011-05-31

申请人： Young Sook Hwang ,  Sang-Bum Kim ,  Chang Hao Yin ,  Zhiyang Wang ,  Qun Liu ,  Yajuan Lv

发明人： Young Sook Hwang ,  Sang-Bum Kim ,  Chang Hao Yin ,  Zhiyang Wang ,  Qun Liu ,  Yajuan Lv

IPC分类号： G06F17/28

CPC分类号： G06F17/2881 ,  G06F17/2818 ,  G06F17/2872

摘要： Disclosure relates to a statistical machine translation field, and more particularly to a method and a device for filtering a translation rule and generating a target word in a hierarchical phrase-based statistical machine translation. The method and device filters a translation rule using a relaxed-well-formed dependency structure and generates a target word by referring to a head word of a source word in a hierarchical phrase-based statistical machine translation. The disclosure improves a translation performance while reducing a number of translation rules, in comparison with a hierarchical phrase-based original translation rule table.

摘要翻译： 公开涉及统计机器翻译领域，更具体地涉及一种用于过滤翻译规则并在基于分层短语的统计机器翻译中生成目标词的方法和装置。 该方法和设备使用轻松完善的依赖结构来过滤翻译规则，并通过参考基于分层短语的统计机器翻译中的源词的头字来生成目标词。 与基于分层短语的原始翻译规则表相比，本公开改善了翻译性能，同时减少了多个翻译规则。

公开(公告)号：US09125157B2

公开(公告)日：2015-09-01

申请号：US13521209

申请日：2011-01-10

申请人： Kyeong-In Jeong ,  Soeng-Hun Kim ,  Jung-Soo Jung ,  Sang-Bum Kim

发明人： Kyeong-In Jeong ,  Soeng-Hun Kim ,  Jung-Soo Jung ,  Sang-Bum Kim

IPC分类号： G08C17/00 ,  H04W52/02 ,  H04W76/04 ,  H04W4/00

CPC分类号： H04W76/28 ,  H04W4/70 ,  H04W52/0216 ,  H04W52/0287 ,  H04W68/005 ,  H04W88/08 ,  Y02D70/00 ,  Y02D70/1224 ,  Y02D70/1242 ,  Y02D70/1262 ,  Y02D70/21 ,  Y02D70/23 ,  Y02D70/24

摘要： Method is provided for communicating with a User Equipment (UE) supporting a High Power Saving Reception Mode (HPSRM) mode by an evolved Node B (eNB) in a wireless communication system. The method includes receiving Discontinuous Reception (DRX) cycle information from a network entity performing mobility management for the UE by the eNB communicating with the UE over a wireless link; and broadcasting system information including the DRX cycle information. The DRX cycle information is set longer than DRX cycle information of a UE non-supporting the HPSRM mode. By doing so, an efficient paging method for an UE operating in the HPSRM mode may be provided.

摘要翻译： 提供了用于与在无线通信系统中的演进型节点B（eNB）支持高功率节省接收模式（HPSRM）模式的用户设备（UE）进行通信的方法。 该方法包括：从eNB通过无线链路与UE进行通信，对从UE进行移动性管理的网络实体接收不连续接收（DRX）周期信息; 以及包括DRX周期信息的广播系统信息。 DRX周期信息被设置为比不支持HPSRM模式的UE的DRX周期信息更长。 通过这样做，可以提供用于以HPSRM模式操作的UE的有效寻呼方法。