公开(公告)号：KR1020150035154A

公开(公告)日：2015-04-06

申请号：KR1020130115387

申请日：2013-09-27

Applicant: 한국전자통신연구원

Inventor： 서영애 ,  김영길 ,  권오욱 ,  김창현 ,  나승훈 ,  노윤형 ,  신종훈 ,  이기영 ,  정상근 ,  최승권 ,  김운 ,  박은진 ,  황금하

IPC: G06F17/28 ,  G06F17/30

CPC classification number: G06F17/30669 ,  G06F17/289 ,  G06F17/30696

Abstract: 자동번역된번역문에서선택된검증대상을이용하여검색정보를생성하고, 생성된검색정보로검색된검색결과들을정보검색소스의신뢰도및 정보검색결과의정확도에기반하여사용자에게제공하도록한 번역검증장치및 방법이제시된다. 제시된번역검증장치는원시언어문장을목적언어문장으로번역하여생성된최종목적언어번역문에포함된단어또는구문을검증대상으로선택하고, 선택된검증대상을근거로생성된복수의검색어들을근거로복수의정보검색소스들로부터검색결과들을검출하고, 정보검색소스의신뢰도및 정보검색결과의정확도를근거로설정된검색결과들의우선순위를근거로복수의검색결과들을제공한다.

Abstract translation: 提供了一种用于验证翻译的装置和方法，其使用从自动翻译文本中选择的验证目标生成搜索信息，并且基于信息搜索源的可靠性和信息搜索结果的准确性，通过生成的搜索信息搜索生成搜索结果。 所提供的用于验证翻译的装置选择以通过将用原始语言书写的句子翻译成以目标语言写成的语言而生成的目标语言中包含的最终翻译文本中包括的单词，短语或句子; 基于在所选择的验证对象的权限上生成的多个搜索词来检测来自多个信息搜索源的搜索结果; 并根据信息搜索源的可靠性和信息搜索结果的准确性，根据搜索结果集的优先级提供搜索结果。

公开(公告)号：KR1020140119841A

公开(公告)日：2014-10-13

申请号：KR1020130032522

申请日：2013-03-27

Applicant: 한국전자통신연구원

Inventor： 김창현 ,  김영길 ,  권오욱 ,  나승훈 ,  노윤형 ,  서영애 ,  양성일 ,  이기영 ,  정상근 ,  최승권 ,  김운 ,  박은진 ,  신종훈 ,  황금하 ,  박상규

IPC: G06F17/28 ,  G06F17/27 ,  G06T13/00

CPC classification number: G06T13/00 ,  G06F17/2854

Abstract: A method for verifying translation by using animation of the present invention can include a process of analyzing a first-language sentence of an original text inputted to be translated in a second language using a translation engine; a process of generating animation which can express a meaning of the first-language sentence using the analyzed result information of the first-language sentence; and a process of providing a user using the original text, with the original text and the generated animation to verify errors in translation.

Abstract translation: 通过使用本发明的动画来验证翻译的方法可以包括使用翻译引擎分析输入要以第二语言翻译的原始文本的第一语言句子的处理; 生成可以使用第一语言句子的分析结果信息来表达第一语言句子的意义的动画的过程; 以及使用原始文本提供用户原始文本和生成的动画以验证翻译中的错误的过程。

公开(公告)号：KR1020140079546A

公开(公告)日：2014-06-27

申请号：KR1020120146914

申请日：2012-12-14

Applicant: 한국전자통신연구원

Inventor： 이기영 ,  권오욱 ,  노윤형 ,  양성일 ,  정상근 ,  최승권 ,  황금하 ,  박은진 ,  김창현 ,  나승훈 ,  서영애 ,  김운 ,  신종훈 ,  김영길 ,  박상규

IPC: G09B19/06 ,  G09B7/04

CPC classification number: G09B19/06 ,  G09B7/04

Abstract: The present invention relates to a foreign language learning apparatus using a dialogue interface. The invention comprises: a corpus including large amount of English sentences; and the dialog interface for suggesting specific situations selectable by a user, for suggesting, to the user, missions to be pursued in the specific situation selected in order to enable the user to select a mission, and for performing conversations with the user. The invention is characterized by using the corpus to understand the intention of a spoken sentence of the user through the dialogue interface, secure link information between the intention understood and the spoken sentence of the user, examine if a grammatical error exists in the spoken sentence of the user, and provide the user with error-corrected knowledge along with an error examined by extracting the error-corrected knowledge corresponding to the examined error. The present invention like the same enables the user to experience various cases by dialogue scenarios of a system in a similar situation, and doubles learning effects by suggesting various expressions to the same user input sentence as a system response.

Abstract translation: 本发明涉及一种使用对话界面的外语学习装置。 本发明包括：包含大量英文句子的语料库; 以及用于建议用户可选择的特定情况的对话界面，用于向用户建议在所选择的特定情况下追求的任务，以使得用户能够选择任务，并且与用户进行对话。 本发明的特征在于使用语料库通过对话界面了解用户的口语句子的意图，确保用户意图理解和口语句子之间的安全链接信息，检查语音句子中是否存在语法错误 并且通过提取与所检查的错误相对应的错误校正的知识来向用户提供错误校正的知识以及检查的错误。 与此相同的本发明使得用户能够通过类似情况下的系统的对话场景来体验各种情况，并且通过向系统响应的相同用户输入语句建议各种表达来加倍学习效果。

公开(公告)号：KR1020140079545A

公开(公告)日：2014-06-27

申请号：KR1020120146912

申请日：2012-12-14

Applicant: 한국전자통신연구원

Inventor： 나승훈 ,  김창현 ,  양성일 ,  서영애 ,  이기영 ,  정상근 ,  권오욱 ,  황금하 ,  신종훈 ,  노윤형 ,  최승권 ,  김운 ,  박은진 ,  김영길 ,  박상규

IPC: G06F17/20 ,  G06F17/30 ,  G06F17/40

CPC classification number: G06F17/2755 ,  G06F17/10

Abstract: The present invention relates to a method for part-of-speech tagging and, more specifically, to a method for multi-language morphological analysis and part-of-speech tagging based on a phrase-based decoding mode. According to the configuration of the present invention, tagging ambiguity can be significantly reduced by taking phrases in part-of-speech tagging units without selecting words with high tagging ambiguity in tagging units and, additionally, various qualities can be effectively used by generalizing an existing word-based HMM model and proposing a robust probabilistic framework using a phrase-based decoding algorithm.

Abstract translation: 本发明涉及一种用于部分语音标签的方法，更具体地，涉及一种基于短语解码模式的多语言形态分析和部分语音标签的方法。 根据本发明的结构，可以通过在词性标签单元中使用短语而不在标签单元中选择具有高标签歧义的单词来显着地减少标记歧义，此外，可以通过将现有的 基于词的HMM模型，并提出了一种使用基于短语的解码算法的鲁棒概率框架。

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

Inventor： 서영애 ,  김창현 ,  양성일 ,  황금하 ,  최승권 ,  노윤형 ,  이기영 ,  권오욱 ,  김운 ,  박은진 ,  신종훈 ,  오영순 ,  김영길 ,  박상규

IPC: G06F17/27 ,  G06F17/28

CPC classification number: G06F17/27 ,  G06F17/28

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

Inventor： 권오욱 ,  김영길 ,  김창현 ,  노윤형 ,  서영애 ,  양성일 ,  이기영 ,  최승권 ,  김운 ,  박은진 ,  신종훈 ,  황금하 ,  박상규

IPC: G06F17/28 ,  G06F17/30 ,  G06F17/25

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

Inventor： 김창현 ,  황금하 ,  서영애 ,  양성일 ,  최승권 ,  노윤형 ,  이기영 ,  권오욱 ,  김운 ,  박은진 ,  신종훈 ,  김영길 ,  박상규

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：KR1020120048139A

公开(公告)日：2012-05-15

申请号：KR1020100109610

申请日：2010-11-05

Applicant: 한국전자통신연구원

Inventor： 노윤형

IPC: G06F17/28

CPC classification number: G06F17/2836

Abstract: PURPOSE: An automatic translation apparatus and a method thereof are provided to increase the coverage of a translation memory and to increase the performance of automatic translation without extension of an additional translation memory. CONSTITUTION: A database searching unit(230) searches for a similar sentence of a translation memory based on a generated keyword. A similarity calculating unit(240) calculates the similarity of similarity sentences based on a weighted value of a word. The word is a word for substituting/deleting/adding to be modified into the input sentence. The weighted value is matched for substituting/deleting/adding a task.

Abstract translation: 目的：提供一种自动翻译装置及其方法，以增加翻译记忆库的覆盖范围，并提高自动翻译的性能，而不需要额外的翻译记忆库的扩展。 构成：数据库搜索单元（230）基于生成的关键字搜索翻译记忆库的类似句子。 相似度计算单元（240）基于单词的加权值来计算相似性句子的相似度。 该词是用于替换/删除/添加以修改为输入句的单词。 匹配替换/删除/添加任务的加权值。

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

Inventor： 양성일 ,  김영길 ,  김창현 ,  권오욱 ,  김운 ,  박은진 ,  서영애 ,  노윤형 ,  황금하 ,  신종훈 ,  최승권 ,  이기영 ,  박상규

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

Inventor： 김운 ,  권오욱 ,  최승권 ,  이기영 ,  신종훈 ,  황금하 ,  노윤형 ,  박은진 ,  서영애 ,  양성일 ,  김창현 ,  김영길 ,  박상규

IPC: G06F17/21 ,  G06F17/27

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）。