-
公开(公告)号：KR1020140117771A
公开(公告)日：2014-10-08
申请号：KR1020130032339
申请日：2013-03-26
Applicant: 한국전자통신연구원
CPC classification number: G06F17/289 , G06F1/1684 , G06F1/1694 , G06F3/017 , G06F3/167
Abstract: Disclosed are a motion sensor-based portable automatic interpretation apparatus which can certainly detect a starting point and an ending point of a speech of a user in the portable automatic interpretation apparatus to improve quality of an automatic interpretation system, and a method for controlling the same. The disclosed apparatus comprises a motion sensing unit sensing the motion of the portable automatic interpretation apparatus; a speech starting point detecting unit detecting a speech starting point based on an output signal from the motion sensing unit; and a speech ending point detecting unit detecting a speech ending point based on an output signal from the motion sensing unit after completing the detection of the speech starting point.
Abstract translation: 公开了一种基于运动传感器的便携式自动解读装置，其能够可靠地检测便携式自动解读装置中的用户的语音的起始点和终点，以提高自动解释系统的质量，以及用于控制自动解释系统的方法 。 所公开的装置包括感测便携式自动解释装置的运动的运动感测单元; 语音起始点检测单元，基于来自运动检测单元的输出信号检测语音起始点; 以及语音结束点检测单元，在完成语音起始点的检测之后，基于来自运动感测单元的输出信号检测语音结束点。
-
公开(公告)号：KR101416098B1
公开(公告)日：2014-07-09
申请号：KR1020100099547
申请日：2010-10-12
Applicant: 한국전자통신연구원
Abstract: 구단위 번역 지식 학습 방법 및 이를 수행하는 장치가 개시된다. 구단위 번역 지식 학습은 먼저, 입력된 양국어 말뭉치 및 원시언어 명사구를 기반으로 상기 원시언어 명사구에 대응되는 목표언어 명사구 번역지식 구축 후보를 선정하고, 양국어 말뭉치 중 원시언어의 자동번역을 수행한 결과에 기초하여 선정된 명사구 번역지식 구축 후보 중 명사구 번역지식을 수집한 후, 수집된 명사구 번역지식을 사용자에게 검증받기 위한 사용자 인터페이스를 제공하고, 검증된 명사구 번역지식을 저장한다. 따라서, 명사구 구단위 번역 지식을 자동으로 학습할 수 있고, 정확하고 신뢰성있는 번역 지식을 확장할 수 있다.
-
公开(公告)号：KR1020140080717A
公开(公告)日：2014-07-01
申请号：KR1020120146174
申请日：2012-12-14
Applicant: 한국전자통신연구원
CPC classification number: G06F17/30002
Abstract: The present invention relates to an apparatus for constructing a task graph in a dialog processing system based on the task graph. The apparatus includes a task graph management interface for providing a client environment that can correct a task graph; a library interface for providing a client environment that can correct a dialog library; a slot system management interface for providing a client environment that can correct a slot system; a task knowledge management interface for providing a client environment that can correct task knowledge; and a dialog system engine for reflecting a knowledge for controlling a corrected dialog flow of the task graph management interface, the library interface, the slot system management interface, and the task knowledge management interface.
Abstract translation: 本发明涉及一种基于任务图在对话处理系统中构建任务图的装置。 该装置包括用于提供可以校正任务图的客户端环境的任务图管理界面; 用于提供可以校正对话库的客户端环境的库接口; 插槽系统管理接口，用于提供可以校正插槽系统的客户端环境; 任务知识管理界面，用于提供可以纠正任务知识的客户端环境; 以及用于反映用于控制任务图管理接口，库接口，时隙系统管理接口和任务知识管理接口的校正对话流的知识的对话系统引擎。
-
公开(公告)号：KR1020140079598A
公开(公告)日：2014-06-27
申请号：KR1020120147536
申请日：2012-12-17
Applicant: 한국전자통신연구원
CPC classification number: G06F17/2854
Abstract: The present invention relates to an apparatus and a method for verifying a context which verify a dual meaning expression of an input sentence and use the verified expression as a context in interpretation or translation according to a user`s context. For said purpose, the present invention comprises: a dual meaning expression verification part for verifying the dual meaning expression in a first input sentence and a reversely translated sentence for the first input sentence by the input of a user; a context generation part for generating the verified dual meaning expression as the context; and a context control part for controlling the generated context to be applied in translating or interpreting the first input sentence or second input sentences inputted after the first input sentence is inputted. The present invention improves interpretation and translation quality of a bidirectional automatic interpretation and translation device and enhances the communication with a communication partner from a quality and a time perspective.
Abstract translation: 本发明涉及一种用于验证验证输入句子的双重含义表达的上下文的装置和方法，并且根据用户的上下文使用经验证的表达作为解释或翻译中的上下文。 为了所述目的，本发明包括：双重意义表达验证部分，用于通过用户的输入验证第一输入句中的双重含义表达和第一输入句的反向翻译句; 用于生成经验证的双重含义表达作为上下文的上下文生成部分; 以及上下文控制部分，用于控制在输入第一输入句子之后输入的第一输入句子或第二输入句子的翻译或解释中应用的生成上下文。 本发明改进了双向自动解释和翻译装置的解释和翻译质量，并且从质量和时间角度增强了与通信伙伴的通信。
-
公开(公告)号：KR1020140079543A
公开(公告)日：2014-06-27
申请号：KR1020120146908
申请日：2012-12-14
Applicant: 한국전자통신연구원
CPC classification number: G06F17/2836 , G06F17/289 , G10L15/26
Abstract: The present invention relates to an automatic interpreting and translating device to interpret and translate a source language into a target language. The automatic interpreting and translating device comprises: a voice recognizing unit to convert a voice of a source language to a text if the voice of the source language is inputted, and convert a voice of a target language to a text if the voice of the target language is inputted; and an automatic translating unit to translate the converted text of the source language to the target language to output a translation result of the target language if the voice of the source language is converted to the text of the source language by the voice recognizing unit, and correct the text of the converted target language to output a translation result of the target language if the voice of the target language is converted to the text of the target language by the voice recognizing unit. Therefore, the automatic interpreting and translating device performs the natural correction to the target language, thereby improving availability and performance of the device.
Abstract translation: 本发明涉及一种解释和翻译源语言为目标语言的自动翻译和翻译装置。 自动解释和翻译装置包括：语音识别单元，如果输入源语言的语音，则将源语言的语音转换为文本，并且如果目标语音的语音被转换为目标语言的语音 输入语言; 以及自动翻译单元，用于将源语言的转换文本转换为目标语言，以便如果通过语音识别单元将源语言的语音转换为源语言的文本，则输出目标语言的翻译结果，以及 如果目标语言的语音被语音识别单元转换成目标语言的文本，则校正转换的目标语言的文本以输出目标语言的翻译结果。 因此，自动解释和翻译装置对目标语言进行自然校正，从而提高设备的可用性和性能。
-
Patent Agency Ranking
公开(公告)号：KR1020140052183A
公开(公告)日：2014-05-07
申请号：KR1020120117399
申请日：2012-10-22
Applicant: 한국전자통신연구원
Abstract: Provided is a dialogue management system which includes a dialogue system data base where dialogue system data base knowledge for generating a system response sentence about a temporary speech sentence is constructed, a dialogue system engine which generates the system response sentence based on the dialogue system base knowledge when a speech sentence of the same words as the temporary speech sentence is inputted, and a user interface which reconstructs or edits the dialogue system base knowledge as dialogue system knowledge according to external command input when there is an error in the system response sentence and performs a test on user intension and language comprehension about the speech sentence.
Abstract translation: 提供了一种对话管理系统，其包括对话系统数据库，其中构建用于生成关于临时语音句子的系统响应语句的对话系统数据库知识;基于对话系统基础知识生成系统响应语句的对话系统引擎 当输入与临时语音句子相同的语音的语句时，以及用户接口，当系统响应语句中存在错误并根据外部命令输入重建或编辑对话系统基础知识作为对话系统知识时，执行 对言语句的用户意图和语言理解的考验。
-
公开(公告)号：KR1020140049150A
公开(公告)日：2014-04-25
申请号：KR1020120114535
申请日：2012-10-16
Applicant: 한국전자통신연구원
IPC: G06F17/28
CPC classification number: G06F17/2854 , G06F17/2818 , G06F17/2872
Abstract: Disclosed are a machine translation post-processing system based on user participation and a method thereof. According to the present invention, the machine translation post-processing system based on user participation includes: a machine translation engine which provides statistical machine translation (SMT) and statistically-enhanced rule-based machine translation (RBMT) using a dual-language corpus database for a source language sentence inputted by a user; a user interface which is used to receives corrections for machine translation results by the machine translation engine from the user; a post-processing rule generator which compares the final sentence corrected through the user interface and the sentence translated by the machine translation engine and generates post-processing rules according to correction details; and an application range re-adjuster which re-adjusts the application range of rules for dual-language corpora based on the post-processing rules generated by the post-processing rule generator. [Reference numerals] (100) Machine translation engine; (110) Dual-language corpus database; (120) Data on a source language sentence and a translated sentence; (130) Translation memory; (200) User interface; (210) Corrected final sentence; (300) Post-processing rule generator; (400) Application range re-adjuster; (500) Post-processing knowledge storage unit; (510) Translation knowledge; (600) Analysis/generation data API; (610) Rules manually written by a user
Abstract translation: 公开了一种基于用户参与的机器翻译后处理系统及其方法。 根据本发明，基于用户参与的机器翻译后处理系统包括：使用双语言语料库数据库提供统计机器翻译（SMT）和统计增强的基于规则的机器翻译（RBMT）的机器翻译引擎 用于由用户输入的源语句; 用户接口，用于由用户接收机器翻译引擎对机器翻译结果的校正; 后处理规则生成器，其将通过用户界面修正的最终句子与由机器翻译引擎翻译的句子进行比较，并根据校正细节生成后处理规则; 以及应用范围重新调整器，其基于由后处理规则生成器生成的后处理规则重新调整双语言语料库规则的应用范围。 （附图标记）（100）机器翻译引擎; （110）双语语料库; （120）源语言句和翻译句的数据; （130）翻译记忆; （200）用户界面; （210）更正最后一句; （300）后处理规则生成器; （400）应用范围重新调整; （500）后处理知识存储单元; （510）翻译知识; （600）分析/生成数据API; （610）用户手动写的规则
-
公开(公告)号：KR1020140049148A
公开(公告)日：2014-04-25
申请号：KR1020120114533
申请日：2012-10-16
Applicant: 한국전자통신연구원
CPC classification number: G06F17/2755 , G06F17/30011
Abstract: Disclosed are a word class tagging method based on morpheme separation and a device thereof. According to one embodiment of the present invention, the word class tagging method includes: a step of performing morpheme separation for a predetermined raw corpus; a step of searching for one or more documents similar to input text based on the result of the morpheme separation; a step of performing domain adaptation of a morpheme separation model and a word class tagging model using the searched similar documents; and a step of tagging word classes to the input text using the morpheme separation model and the word class tagging model to which domain adaptation is performed. The searching step uses a search database which is built by processing a group of documents in which the raw corpus is separated by morpheme based on the result of the morpheme separation or uses a plurality of clusters acquired by clustering the documents in which the raw corpus is separated by morpheme based on the result of the morpheme separation. By doing so, even if the word spacing among morphemes of the raw corpus is not clear, it is possible to perform domain adaptation of morpheme separation and word class tagging and to remove limitation of linguistic expandability. [Reference numerals] (AA) Start; (BB) End; (S110) Perform morpheme separation for a large-volume raw corpus; (S120) Search for documents similar to input text based on the morpheme separation result; (S130) Perform domain adaptation of a morpheme separation model and a word class tagging model using the searched similar documents; (S140) Tag word classes to the input text using the morpheme separation model and the word class tagging model to which domain adaptation is performed
Abstract translation: 公开了基于语素分离的词类标记方法及其装置。 根据本发明的一个实施例，词类标记方法包括：对预定原始语料库执行语素分离的步骤; 基于语素分离的结果搜索类似于输入文本的一个或多个文档的步骤; 使用搜索到的类似文档执行语素分离模型和单词类标签模型的域适配的步骤; 以及使用语素分离模型和执行域适配的单词类标签模型将单词类标记到输入文本的步骤。 搜索步骤使用搜索数据库，该搜索数据库是通过处理基于语素分离的结果的原始语料库被语素分离的一组文档来构建的，或者使用通过聚集原始语料库 基于语素分离结果的语素分离。 通过这样做，即使原始语料的语素之间的词间距不清楚，也可以进行语素分离和词类标注的领域适应，并消除语言扩展性的限制。 （附图标记）（AA）开始; （BB）结束; （S110）对大容量原始语料库执行语素分离; （S120）基于语素分离结果搜索类似于输入文本的文档; （S130）使用搜索到的类似文档对语素分离模型和单词类标注模型进行域适应; （S140）使用语素分离模型和进行域自适应的单词分类模型对输入文本进行标记词类
-
公开(公告)号：KR1020130123037A
公开(公告)日：2013-11-12
申请号：KR1020120046137
申请日：2012-05-02
Applicant: 한국전자통신연구원
IPC: G06Q50/30
CPC classification number: G06F17/289 , G06F17/2863 , G06F17/2872
Abstract: The present invention relates to an apparatus and method for providing a two-way automatic interpretation and translation service comprising: a first interpretation and translation unit for interpreting and translating a first language into a second language; a second interpretation and translation unit for interpreting and translating the second language into the first language; and a context information management unit for receiving conversational context and translation history information, and sharing and managing the conversational context and translation history information; wherein each of the first and second interpretation and translation units provides an interpretation service for receiving an input conversation in the first or second language in speech and outputting results of interpretation in speech in the second or first language, and a translation service for receiving an input conversation in the first or second language in text and outputting results of translation in text in the second or first language. [Reference numerals] (100) First interpretation and translation unit;(200) Second interpretation and translation unit;(300) Context information managing unit;(400) Two-way communication unit;(410) Context record managing unit;(420) Context translation information DB
Abstract translation: 本发明涉及一种用于提供双向自动解释和翻译服务的装置和方法，包括：用于将第一语言解释和翻译成第二语言的第一解释和翻译单元; 第二个翻译单位，用于将第二语言翻译成第一语言; 以及上下文信息管理单元，用于接收对话上下文和翻译历史信息，以及共享和管理会话语境和翻译历史信息; 其中第一和第二解释和翻译单元中的每一个提供用于在语音中接收第一或第二语言的输入会话的解释服务，并输出具有第二或第一语言的语音中的解释结果，以及用于接收输入的翻译服务 在第一语言或第二语言中的文本中的对话，并以第二语言或第一语言输出文本中的翻译结果。 （100）第一解释和翻译单元;（200）第二解释和翻译单元;（300）上下文信息管理单元;（400）双向通信单元;（410）上下文记录管理单元;（420） 上下文翻译信息DB
-
120.发明公开중국어 자동 번역을 위한 생략 성분 복원 방법 및 장치, 이를 포함하는 중국어 자동 번역 방법 및 장치 无效用于中国机器翻译的中国机器翻译的方法和装置，用于包含它们的中文机翻译的方法和装置
公开(公告)号：KR1020130102926A
公开(公告)日：2013-09-23
申请号：KR1020120024128
申请日：2012-03-08
Applicant: 한국전자통신연구원
CPC classification number: G06F17/2863 , G06F17/2755
Abstract: PURPOSE: An omitted component restoration method and an apparatus for Chinese machine translation, and a Chinese machine translation method and an apparatus including the same are provided to classify an omitted expression included in a Chinese dialogue sentence, and to restore the omitted expression according an omission type, thereby providing an accurate auto-translation result. CONSTITUTION: An input Chinese dialogue sentence is divided into work units, and the property is extracted based on morpheme analysis information with respect to the division result and the word (S1100). An omission type of the input Chinese dialogue sentence is estimated based on the extracted property (S1200). The omitted portion of the input Chinese dialogue sentence is restored according to the omission type (S1300). The estimation probability of the omitted component is improved by using the morpheme analysis information with respect to the word, and the morpheme analysis information includes the part of speech of the word and definition information. [Reference numerals] (AA) Start; (BB) End; (S1000) Divide an input Chinese dialogue into word units; (S1100) Extract the properties to determine whether there is any element deleted from the input Chinese dialogue sentence and to estimate the omission type based on the result of dividing the sentence into word units and morpheme analysis information with respect to each word; (S1200) Estimate an omission type of the input Chinese dialogue sentence based on the extracted property; (S1300) Restore the deleted element based on the estimated omission type
Abstract translation: 目的：提供一种省略的部件恢复方法和中文机器翻译装置，以及一种中文机器翻译方法及其装置，用于对包含在中文对话句中的省略表达进行分类，并根据省略恢复省略的表达 类型，从而提供准确的自动翻译结果。 构成：输入中文对话句分为工作单位，根据分词结果和单词的语素分析信息提取属性（S1100）。 基于所提取的属性来估计输入的中文对话句的省略类型（S1200）。 输入中文对话句的省略部分根据省略类型进行恢复（S1300）。 通过使用关于该词的语素分析信息来提高省略的分量的估计概率，并且语素分析信息包括单词和定义信息的部分语音。 （附图标记）（AA）开始; （BB）结束; （S1000）将输入的中文对话划分为字单位; （S1100）提取属性，以确定是否从输入的中文对话句中删除任何元素，并根据将句子分为单词和词素分析信息的结果来估计遗漏类型; （S1200）基于提取的属性估计输入的中文对话句的省略类型; （S1300）根据估计的省略类型恢复已删除的元素
-
-
-
-
-
-
-
-
-
Search Results
139
records
(took 0.041 seconds)
