-
公开(公告)号：KR1020120105063A
公开(公告)日：2012-09-25
申请号：KR1020100129425
申请日：2010-12-16
Applicant: 한국전자통신연구원
Abstract: PURPOSE: A dropped component restoration method and apparatus therefor are provided to create correct translation by providing correct predicate phrase information. CONSTITUTION: A morpheme analysis unit(201) analyzes the morpheme of a target language and a received original language. A dropped component recognition unit(203) recognizes whether dropped components are generated using original language information analyzed by a sentence structure analysis unit(202). An antecedent recognition unit(205) recognizes subject information corresponding to the dropped predicate phrase. A sentence attribute extraction unit(204) extracts sentence attribute information. A dropped component restoration unit(206) creates the dropped component restoration information. [Reference numerals] (203) Dropped component recognition unit; (204) Sentence attribute extraction unit; (205) Antecedent recognition unit; (206) Dropped component restoration unit; (211) First morpheme analysis unit; (212) First sentence structure analysis unit; (221) Second morpheme analysis unit; (222) Second sentence structure analysis unit; (AA) Source language; (BB) Bilingual text information of a purpose language; (CC) Dropped component restoration information
Abstract translation: 目的：提供一种丢弃的组件恢复方法及其设备，通过提供正确的谓词短语信息来创建正确的翻译。 构成：语素分析单元（201）分析目标语言和接收到的原始语言的语素。 丢弃分量识别单元（203）通过由句子结构分析单元（202）分析的原始语言信息来识别是否产生丢弃的分量。 先前识别单元（205）识别与丢弃的谓词短语相对应的被摄体信息。 句子属性提取单元（204）提取句子属性信息。 丢弃组件恢复单元（206）创建丢弃的组件恢复信息。 （附图标记）（203）丢弃部件识别部; （204）句子属性提取单元; （205）先前识别单位; （206）掉落部件恢复单元; （211）第一语素分析单元; （212）第一句结构分析单位; （221）第二语素分析单元; （222）第二句结构分析单位; （AA）来源语言; （BB）目的语言的双语文本信息; （CC）丢弃组件恢复信息
-
公开(公告)号：KR1020120072196A
公开(公告)日：2012-07-03
申请号：KR1020100134029
申请日：2010-12-23
Applicant: 한국전자통신연구원
CPC classification number: G06F17/2836 , G06F17/25
Abstract: PURPOSE: A translation system and a translation method thereof are provided to reduce time and cost for translation by automatically generating variable elements in a translation memory. CONSTITUTION: A basic translation unit(10) translates word in translation database into a second language. A variable element generation unit searches for variable elements which are translated by automata. A variable element translation unit(20) translates a sentence of a first language based on the content of the variable element generation unit into the second language. An automatic translation unit performs automatic translation of the word.
Abstract translation: 目的：提供翻译系统及其翻译方法，以通过在翻译记忆库中自动生成可变元素来减少翻译的时间和成本。 构成：基本翻译单元（10）将翻译数据库中的单词翻译成第二语言。 可变元素生成单元搜索由自动机翻译的可变元素。 可变元素翻译单元（20）将基于可变元素生成单元的内容的第一语言的句子翻译成第二语言。 自动翻译单元执行单词的自动翻译。
-
公开(公告)号：KR1020120064555A
公开(公告)日：2012-06-19
申请号：KR1020100125835
申请日：2010-12-09
Applicant: 한국전자통신연구원
IPC: G06F17/28
CPC classification number: G06F17/28 , G06F17/3053
Abstract: PURPOSE: A method and apparatus for verb pattern matching in Korean machine translation are provided to improve matching accuracy and pattern reappearance by differentiating a semantic preference point and a preference point of declension argument. CONSTITUTION: Apparatus for verb pattern matching in Korean machine translation comprises: a pattern point calculator(110) calculating preference point according to matched argument about one or more predicate pattern candidates; a bonus point calculator(130) giving a penalty point to the preference point, and excluding predicate pattern candidate with preference point under standard point; and a pattern selection unit(150) selecting pattern corresponding with an input sentence according to the preference point for the predicate pattern candidates.
Abstract translation: 目的：提供韩国机器翻译中动词模式匹配的方法和装置，以通过区分语义偏好点和声明参数的偏好点来提高匹配精度和模式重现。 构成：韩国机器翻译中用于动词模式匹配的装置包括：模式点计算器（110）根据关于一个或多个谓词模式候选的匹配参数来计算偏好点; 给予偏好点惩罚点的奖励点计算器（130），并且在标准点以下排除具有偏好点的谓词模式候选者; 以及模式选择单元，根据谓词模式候选的偏好点选择与输入句子对应的模式。
-
公开(公告)号：KR1020120035077A
公开(公告)日：2012-04-13
申请号：KR1020100096572
申请日：2010-10-04
Applicant: 한국전자통신연구원
IPC: G06F17/28
CPC classification number: G06F17/289 , G06F17/2755 , G06F17/2836
Abstract: PURPOSE: An automatic hybrid translation method and an apparatus performing the same are provided to prevent undesired effect in an automatic translation environment which uses an automatic translation system. CONSTITUTION: A comparing unit(320) determines whether a sentient is an automatic hybrid translation object. A translation engine unit(330) performs automatic translation of a node part in a sentence through a translation engine. The translation engine unit generates an object language. An integration unit(340) integrates the reference translation data and the generated object language.
Abstract translation: 目的：提供自动混合翻译方法和执行该自动混合翻译方法的装置，以防止在使用自动翻译系统的自动翻译环境中的不期望的影响。 构成：比较单元（320）确定有情者是自动混合翻译对象。 翻译引擎单元（330）通过翻译引擎对句子中的节点部分进行自动翻译。 翻译引擎单元生成对象语言。 集成单元（340）集成了参考翻译数据和生成的对象语言。
-
公开(公告)号：KR1020120035076A
公开(公告)日：2012-04-13
申请号：KR1020100096570
申请日：2010-10-04
Applicant: 한국전자통신연구원
CPC classification number: G06F17/2785 , G06F17/2755 , G06F17/2818
Abstract: PURPOSE: A parallel corpus constructing method using a middle language is provided to construct an automatic parallel corpus about a pair of languages having insufficient resources. CONSTITUTION: A first parallel corpus between an middle language and a first language and a second parallel corpus between the middle language and a second language are collected(110). Similarity between a middle language version of the first parallel corpus and a middle language version of the second parallel corpus is analyzed(120). A parallel corpus candidate document of the first language and the second language is extracted based on the analyzed similarity(130).
Abstract translation: 目的：提供一种使用中间语言的并行语料库构造方法，构建一种关于一种语言资源不足的自动并行语料库。 组合：收集中间语言和第一语言之间的第一个平行语料库和中间语言和第二语言之间的第二个平行语料库（110）。 分析第一个平行语料库的中间语言版本与第二个并行语料库的中间语言版本之间的相似性（120）。 基于分析的相似度提取第一语言和第二语言的并行语料库候选文档（130）。
-
Patent Agency Ranking
公开(公告)号：KR101092363B1
公开(公告)日：2011-12-09
申请号：KR1020080130777
申请日：2008-12-22
Applicant: 한국전자통신연구원
Abstract: 본발명은중한자동번역을위한한국어연결어미생성방법및 그장치에관한것으로, 중/한자동번역에서명시적인어휘로절 간논리연결을표현하지않은중국어문장을한국어로번역하는경우에있어서, 번역한한국어의절 간에명시적인논리연결로표현하지못하는문제점을해결하여한국어연결어미로절 간의논리연결을명시적으로표현하여중국어원문의의미를자연스러운한국어문장으로자동번역함으로써중/한자동번역의번역성능을향상시킬수 있다. 또한, 본발명은번역할중국어원문이비명시적인중국어의단문논리연결을가질경우에한국어관점에서명시적인연결어미를생성하여한국어문장을생성함으로써, 중국어원문의원래의미를그대로가지면서높은품질의한국어를생성할수 있다.
-
公开(公告)号：KR1020110070632A
公开(公告)日：2011-06-24
申请号：KR1020090127522
申请日：2009-12-18
Applicant: 한국전자통신연구원
CPC classification number: G06F17/271 , G06F17/274 , G06F17/2785
Abstract: PURPOSE: Apparatus and method for relation classification using quantified related information are provided to improve the accuracy of the relation classification by expressing relation candidates on a basis of quantified related information. CONSTITUTION: A relation candidate extracting unit(110) extracts classification object relation candidates from language corpus using a lexical pattern. A grammatical feature generation unit(120) generates grammatical features of the classification object relation candidates. A meaning feature generation unit(130) generates meaning features of two terms forming classification object relation candidates. A relatedness feature generation unit(140) generates quantified relatedness information of the classification object relation candidates. A relatedness classification unit(150) classifies the classification object relation candidates in a relation type using grammatical features, meaning features, and relatedness feature information.
Abstract translation: 目的：提供使用量化相关信息的关系分类的装置和方法，以通过基于量化的相关信息表达关系候选来提高关系分类的准确性。 构成：关系候选提取单元（110）使用词汇模式从语言语料库中提取分类对象关系候选。 语法特征生成单元（120）生成分类对象关系候选者的语法特征。 意义特征生成单元（130）生成形成分类对象关系候选的两个项的意义特征。 相关性特征生成单元（140）生成分类对象关系候选的量化关联性信息。 相关性分类单元（150）使用语法特征，含义特征和相关性特征信息来分类关系类型中的分类对象关系候选。
-
公开(公告)号：KR101023210B1
公开(公告)日：2011-03-18
申请号：KR1020080127709
申请日：2008-12-16
Applicant: 한국전자통신연구원
Abstract: 본 발명은 구문 분석 방법 및 그 장치에 관한 것으로, 비활성 챠트를 생성할 경우 미리 구축된 제약조건을 매칭시켜 챠트 생성을 방지 혹은 챠트 가중치를 조정하거나 특정 액션을 수행함으로써, 구문 모호성 처리를 용이하게 수행할 수 있다. 또한, 본 발명은 제약조건 규칙을 적용하여 구문 모호성을 해결하도록 함으로써, 기존에서와 같이 증가된 CFG의 조건이 부여됨에 따라 다르게 적용되는 규칙의 증가와 이 규칙간의 우선순위를 조정하는데 어려움이 있었던 문제점을 해결할 수 있다.
구문분석, 챠트 파싱, 제약 조건, 모호성 처리-
公开(公告)号：KR1020110024889A
公开(公告)日：2011-03-09
申请号：KR1020090083069
申请日：2009-09-03
Applicant: 한국전자통신연구원
CPC classification number: G06F17/289 , G06F17/2745
Abstract: PURPOSE: A device and a method for verifying translation knowledge which is specialized in a domain are provided to automatically classify translation knowledge which is most adaptive in a corresponding domain by using parallel corpus per domain. CONSTITUTION: A lemma indexer(106) disperse a plurality of lemma indexed parallel corpus to a plurality of cluster servers. Through constructed translation knowledge, a reference translator automatically translates the lemma indexed parallel corpus. Through translation knowledge of a verification target, an evaluation translator(121) automatically translates the lemma indexed parallel corpus. An auto evaluation unit(118) compares a translation performance difference of a reference translation result(116) and an evaluation translation result(123).
Abstract translation: 目的：提供一种用于验证专业于域的翻译知识的设备和方法，以通过使用每个域的平行语料库自动分类在相应域中最适合的翻译知识。 构成：引理索引器（106）将多个引理索引平行语料库分散到多个群集服务器。 通过构建的翻译知识，参考翻译器自动翻译引文索引的平行语料库。 通过验证目标的翻译知识，评估翻译器（121）自动翻译引文索引平行语料库。 自动评估单元（118）比较参考翻译结果（116）和评估翻译结果（123）的翻译性能差异。
-
90.发明公开
公开(公告)号：KR1020100073164A
公开(公告)日：2010-07-01
申请号：KR1020080131758
申请日：2008-12-22
Applicant: 한국전자통신연구원
IPC: G06F17/40
CPC classification number: G06F17/2765 , G06F17/2755 , G06F17/289 , G06F17/30737
Abstract: PURPOSE: A substitute language specializing device and a method thereof are provided to extract air vocabulary through primitive language corpus and a target language corpus belongings to a target domain and extract substitute language candidate and reflect representative substitute language to substitute dictionary, thereby reducing the cost by manual. CONSTITUTION: A vocabulary arrangement unit(106) extracts co-occurrence vocabulary through primitive language tagged corpus and target language tagged corpus. The vocabulary arrangement unit extracts substitute candidates with mapping of band relation of co-occurrence vocabularies about a substitute dictionary. An error filtering unit(108) determines representative substitute language with filtering of substitute relation error about the extracted substitute candidate. A substitute dictionary reflector(110) reflects the determined representative substitute to the substitute dictionary.
Abstract translation: 目的：提供替代语言专业设备及其方法，通过原语言语料库和目标语言语料库提取空中词汇，并提取替代语言候选词，并反映代表性替代语言来替代词典，从而降低成本 手册。 构成：词汇排列单元（106）通过原语语言标注语料库和目标语言标签语料库提取同现词汇。 词汇排列单元通过对替代词典的同现词汇的频带关系的映射来提取替代候选。 错误过滤单元（108）通过对提取的替代候选者的替代关系错误进行滤波来确定代表性替代语言。 替代字典反射器（110）将确定的代表性替代物反映到替代字典。
-
-
-
-
-
-
-
-
-
Search Results
123
records
(took 0.029 seconds)
