-
公开(公告)号：KR1020150113280A
公开(公告)日：2015-10-08
申请号：KR1020140036094
申请日：2014-03-27
Applicant: 한국전자통신연구원
IPC: G01C21/36 , G10L15/22 , G06F3/16 , G08G1/0969
CPC classification number: G01C21/3608 , G10L15/22 , G10L2015/223 , G06F3/16 , G08G1/0969
Abstract: 음성대화를이용한네비게이션제어장치및 방법이개시된다. 본발명에따른네비게이션제어장치는사용자로부터음성명령을획득하는음성획득부; 상기사용자의차량에설치되어있는네비게이션의구동정보및 상기차량의상태정보를포함하는차량데이터들을획득하는정보획득부; 상기음성명령을컴퓨터가이해할수 있는사용자의도로변환하는음성대화이해부; 상기차량데이터들중 상기사용자의도에상응하는관련정보를추출하는관련정보추출부; 및상기관련정보및 사용자의도를이용하여상기음성명령에대한대화응답을생성하고, 상기대화응답에상응하도록상기네비게이션을제어하는음성대화관리제어부를포함한다.
Abstract translation: 公开了一种使用语音对话来控制导航装置的装置和方法。 根据本发明的用于控制导航装置的装置包括从用户获取语音命令的语音获取单元; 信息获取单元获取包括关于车辆状态的信息和安装在用户车辆中的导航装置的操作的车辆数据; 语音对话理解单元将语音命令转换成计算机可以理解的用户命令; 信息抽取单元，从车辆数据抽取与用户命令对应的相关信息; 以及语音对话管理控制单元，通过使用相对信息和用户命令来生成关于语音命令的会话响应，并且控制导航以对应于会话响应。
-
公开(公告)号：KR1020150068663A
公开(公告)日：2015-06-22
申请号：KR1020130154590
申请日：2013-12-12
Applicant: 한국전자통신연구원
CPC classification number: G06F17/28 , G06F17/279
Abstract: 본발명은로그데이터를이용한자동번역장치및 그방법에관한것으로, 번역을요청한사용자로부터로그데이터를수집하는로그수집부; 상기사용자의단말로부터입력된발화문장및 상기로그데이터를분석한결과를토대로상기발화문장에해당하는발화상황을인식하고분류하는로그데이터처리부; 및분류된발화상황을토대로상기발화문장에대한번역지식을생성하고관리하는번역지식관리부;를포함하는것을특징으로한다.
Abstract translation: 本发明涉及使用日志数据的自动翻译装置及其方法，其中，所述装置包括：日志收集单元，用于从请求翻译的用户收集日志数据; 日志数据处理单元，用于基于分析语音发言语句的结果和由用户终端输入的日志数据来识别和分类对应于语音发言语句的情况; 以及翻译知识管理单元，用于基于分类的语音话语情况产生与语音话语句相关的翻译知识，并对其进行管理。
-
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
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
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
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。
-
Patent Agency Ranking
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
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：KR1020140077783A
公开(公告)日：2014-06-24
申请号：KR1020120146917
申请日：2012-12-14
Applicant: 한국전자통신연구원
Inventor： 황금하
IPC: G06F17/27
CPC classification number: G06F17/277 , G06F17/2795
Abstract: The present invention provides an apparatus for defining a sense tagging level of a word. The apparatus includes: a field term recognition unit which recognizes a field of words relative to a dialog corpus sense-tagged through a thesaurus; a high-frequency word concept extraction unit which extracts high-frequency word concepts from the field of the words and creates and outputs a high-frequency word concept tree; a high-frequency word concept pair extraction unit which creates and outputs high-frequency word concept pairs that pair high-frequency word concepts with high relevance among the extracted high-frequency word concepts; and a sense tagging level definition unit which defines sense tagging levels and relations therebetween, based on the outputted high-frequency word concept tree and the high-frequency word concept pairs.
Abstract translation: 本发明提供一种用于定义单词的感测标记级别的装置。 该装置包括：字段项识别单元，其识别相对于通过同义词库有意义标记的对话语料库的单词的字段; 高频词概念提取单元，从字段提取高频词概念，并创建并输出高频词概念树; 一种高频字概念对提取单元，其创建并输出在所提取的高频词概念中将高频词概念与高相关性配对的高频字概念对; 以及基于输出的高频词概念树和高频词概念对来定义其间的感应标签级别和关系的感测标签级别定义单元。
-
公开(公告)号：KR101365944B1
公开(公告)日：2014-02-24
申请号：KR1020100079377
申请日：2010-08-17
Applicant: 한국전자통신연구원
Abstract: 본 발명은 통계기반 자동번역 시스템의 인코더인 단어 및 구단위 정렬기에서 학습한 구단위 정렬 결과를 이용하여 패턴기반 자동번역 시스템에서 사용 가능한 구단위 패턴 구축 장치에 관한 것으로, 양국어 병렬 말뭉치에서의 원언어에 대하여 구문분석을 실행하는 원언어 구문 분석부; 상기 양국어 병렬 말뭉치로부터 구단위 정렬 테이블을 생성하는 단어 및 구단위 정렬부; 구문분석 결과에 따라 상기 구단위 정렬 테이블에서 원언어 구단위 제약에 맞는 구만 추출한 후, 일반화 및 정렬 보정하여 패턴 후보를 생성하는 패턴 일반화 및 정렬 보정부; 상기 패턴 후보에 대한 점수를 책정하여 신뢰도가 낮거나 서로 충돌 또는 중복되는 패턴 후보는 필터링하는 패턴 점수화 및 필터링부; 및 상기 필터링된 패턴 후보 중 시스템의 기존 패턴과 충돌 및 중복되지 않는 패턴 후보를 필요 패턴으로 선택하는 필요 패턴 출력부를 포함할 수 있다.
-
公开(公告)号：KR1020130047471A
公开(公告)日：2013-05-08
申请号：KR1020110112524
申请日：2011-10-31
Applicant: 한국전자통신연구원
CPC classification number: G06F17/2818 , G06F17/2827 , G06F17/28 , G06F17/30867 , G06F17/40
Abstract: PURPOSE: A paraphrasing data construction method of an automatic translation system is provided to automatically construct paraphrasing data based on the automatic translation result of an original text, an object language model, and bilingual language corpuses, thereby constructing consistent paraphrasing data. CONSTITUTION: A paraphrasing unit selects a paraphrasing object sentence by applying an object language model to a translation(S120). The paraphrasing unit extracts paraphrasing candidates and paraphrasing object sentence from an original word corpus database(S140). The paraphrasing unit selects the final paraphrasing candidate by applying the object language model to an automatic translation result for the paraphrasing candidates(S160). The paraphrasing unit determines the paraphrasing object sentence and the final paraphrasing candidate as a paraphrasing vocabulary pattern and stores the same in a paraphrasing database(S180). [Reference numerals] (AA) Start; (BB) End; (S110) Output a pair of an original and a translation by automatically translating the original; (S120) Select a paraphrasing object sentence by applying an n-gram based object language model to the translation; (S130) Select a part to be paraphrased; (S140) Extract paraphrasing candidates similar to the selected part in an original word corpus DB; (S150) Automatically translate the paraphrasing candidates; (S160) Select the final paraphrasing candidate by applying the n-gram based object language model to an automatic translation result; (S170) Determine and store the paraphrasing object sentence and the final paraphrasing candidate as a paraphrasing vocabulary pattern using a bilingual corpus; (S180) Extract and store a paraphrasing generalized pattern based on the paraphrasing vocabulary pattern
Abstract translation: 目的：提供一种自动翻译系统的释义数据构建方法，根据原文，对象语言模型和双语语料库的自动翻译结果自动构建改写数据，从而构建一致的释义数据。 构成：翻译单位通过将对象语言模型应用于翻译来选择释义对象句（S120）。 释义单位从原始语料库数据库中提取释义候选人和释义对象句（S140）。 释义单位通过将对象语言模型应用于释义候选者的自动翻译结果来选择最终释义候选（S160）。 释义单位将释义对象句和最终释义候选人确定为释义词汇模式，并将其存储在释义数据库中（S180）。 （附图标记）（AA）开始; （BB）结束; （S110）通过自动翻译原件输出一对原件和翻译件; （S120）通过在翻译中应用基于n-gram的对象语言模型来选择一个释义对象句子; （S130）选择要释义的部分; （S140）提取类似于原始单词语料库DB中所选部分的释义候选词; （S150）自动翻译释义候选人; （S160）通过将基于n-gram的对象语言模型应用于自动翻译结果来选择最终释义候选者; （S170）使用双语语料库确定并存储释义对象句和最终释义候选人作为改写词汇模式; （S180）基于改写词汇模式提取并存储一个释义广义模式
-
公开(公告)号：KR1020130026717A
公开(公告)日：2013-03-14
申请号：KR1020110090047
申请日：2011-09-06
Applicant: 한국전자통신연구원
CPC classification number: G06F17/2836 , G06F17/271 , G06F17/2755 , G06F17/2872
Abstract: PURPOSE: A translation device based on a simultaneous processing pattern and a method thereof are provided to use the simultaneous processing pattern, thereby reducing expenses of knowledge construction. CONSTITUTION: A bilingual text generator(130) generates a bilingual text based on a syntax analysis result of a syntax analyzer(120). A morpheme analyzer(110) extracts a simultaneous processing pattern from an input text based on a parallel corpus. The syntax analyzer analyzes syntax of the input text based on the simultaneous processing pattern. The bilingual text generator generates a translation text based on the syntax analysis result. The morpheme analyzer analyzes and outputs a morpheme of the input text. The bilingual text generator generates the translation text based on a syntax structure. [Reference numerals] (110) Morpheme analyzer; (111) Morpheme analysis unit; (112) Simultaneous processing target recognizing unit; (113) Analysis simultaneous processing unit; (114) Morpheme tagging unit; (120) Syntax analyzer; (130) Bilingual text generator; (131) Generation simultaneous processing unit; (132) Bilingual text generating unit; (141) Simultaneous processing word list; (142) Simultaneous processing pattern DB; (AA) Input sentence; (BB) Translated sentence
Abstract translation: 目的：提供基于同时处理模式的翻译装置及其方法，以使用同时处理模式，从而减少知识构建的费用。 构成：双语文本生成器（130）基于语法分析器（120）的语法分析结果生成双语文本。 语素分析器（110）基于平行语料库从输入文本中提取同时处理模式。 语法分析器基于同时处理模式分析输入文本的语法。 双语文本生成器根据语法分析结果生成翻译文本。 语素分析器分析并输出输入文本的语素。 双语文本生成器基于语法结构生成翻译文本。 （附图标记）（110）语素分析仪; （111）语素分析单位; （112）同时处理目标识别单元; （113）分析同步处理单元; （114）语素标签单位; （120）语法分析器; （130）双语文本生成器; （131）同步处理单元; （132）双语文本生成单元; （141）同时处理单词列表; （142）同时处理图案DB; （AA）输入句; （BB）翻译句
-
-
-
-
-
-
-
-
-
Search Results
123
records
(took 0.026 seconds)
