-
公开(公告)号：KR1020050042696A
公开(公告)日：2005-05-10
申请号：KR1020030077755
申请日：2003-11-04
Applicant: 한국전자통신연구원
IPC: G06F17/27
Abstract: 한국어 부사의 구문 분석 장치 및 방법이 개시된다. 데이터베이스부는 한국어 부사에 대한 피수식어 품사정보, 의미 자질정보, 문법 기능소 정보, 위치 정보 및 확률 정보를 포함하는 패턴정보를 저장한다. 독출부는 분석대상 부사의 패턴정보를 데이터베이스부로부터 독출한다. 피수식어 후보 선택부는 독출한 패턴정보의 피수식어 품사정보를 이용하여 분석대상 부사의 피수식어 후보들을 선택한다. 피수식어 결정부는 독출한 패턴정보의 품사정보, 의미 자질정보, 문법 기능소 정보, 위치 정보 및 확률 정보를 기초로 각각의 피수식어 후보에 대한 소정의 점수를 계산하여 피수식어를 결정한다. 이로써, 한국어 부사의 구조 분석 정확률을 높이며 정확한 부사 구조 분석률을 기초로 술어-인자 및 술어-술어간의 구조 분석에 이용하여 전체 구조 분석의 정확률을 높인다.
-
公开(公告)号：KR1020040056642A
公开(公告)日：2004-07-01
申请号：KR1020020083163
申请日：2002-12-24
Applicant: 한국전자통신연구원
IPC: G06F17/27
Abstract: PURPOSE: A sentence structure analyzing method is provided to parse each sentence by the unit of a clause, and to analyze a total sentence for translating the sentence in a machine translation system so that it enhances a translation quality. CONSTITUTION: The method comprises several steps. An original sentence is input, a syntax pattern generator transmits the original sentence to a morpheme analyzer and a tagger, and a syntax pattern is generated via a morpheme analysis, a tagging and a partial sentence parsing(S101). A clause structure parsing is performed for the generated syntax pattern from a sentence end to a sentence top(S102). A short sentence recognition is performed via a start point sensing, an end point sensing, and a short sentence reduction(S103). A rule matching process for each clause is performed in order to check whether there exists a rule matched with a current syntax pattern(S104). A combination candidate set between clauses is generated(S105). A clause structure tree for all the possible combination sets is generated, a weight value for each tree is calculated, and each candidate set is arranged on a basis of the calculated weight value(S106).
Abstract translation: 目的：提供句子结构分析方法，以句子为单位来分析每个句子，并分析整个句子以翻译机器翻译系统中的句子，从而提高翻译质量。 构成：该方法包括几个步骤。 输入原始句子，语法模式生成器将原始语句发送到语素分析器和标签器，并通过语素分析，标签和部分句子解析生成语法模式（S101）。 对于从语句结尾到句子顶部的生成的语法模式执行子句结构解析（S102）。 通过起点感测，终点感测和短句减少来执行短句识别（S103）。 执行每个子句的规则匹配处理，以便检查是否存在与当前语法模式匹配的规则（S104）。 生成子句之间的组合候选者（S105）。 生成用于所有可能的组合集合的子句结构树，计算每个树的权重值，并且基于所计算的权重值来排列每个候选集（S106）。
-
公开(公告)号：KR100420474B1
公开(公告)日：2004-03-02
申请号：KR1020000083295
申请日：2000-12-27
Applicant: 한국전자통신연구원
IPC: G06F17/28
Abstract: PURPOSE: A long sentence translation system and method is provided to reduce a length of a long sentence to be translated via a sentence division, a short sentence translation or a replacement, and to repeat a sentence frame matching and a combination of the partial sentence frames step by step for performing a semantically natural translation or solving a coverage problem occurred at a sentence frame translation. CONSTITUTION: The method comprises steps of performing preprocesses such as a morpheme analysis, a determination of parts of speech, a recognition of fixed expressions, a discovery of a protector or an analysis of a part separation(201), performing a sentence division on slot queues resulted from the preprocesses for dividing one long English sentence into one more short sentences(202), recognizing the divided short sentences and translating the short sentences by matching a sentence frame(203), determining if the short sentences are successfully translated(204), if the short sentences are successfully translated, replacing a divided sentence, corresponding to a partial sentence frame, with a sentence structure node, and translating all the sentence frames while searching the sentence frames(205), determining if all the sentence frames are successfully translated(206), if they are not, trying a translation by combining the partial sentence frames according to an inter-phrase structure analysis rule(207), and checking if the partial sentence translation is successful(208).
Abstract translation: 目的：提供长句翻译系统和方法，以通过句子分段，短句翻译或替换来减少要翻译的长句子的长度，并且重复句子框匹配和部分句子框的组合 逐步执行语义上自然的翻译或解决在句子框架翻译处发生的覆盖问题。 结构：该方法包括执行诸如词素分析，词类的确定，固定表达的识别，保护者的发现或部分分离的分析等预处理（201），在时隙上执行句子分割 用于将一个长英文句子分成多个短句的预处理所产生的队列（202），识别分开的短句并通过匹配句框来翻译短句（203），确定短句是否被成功翻译（204） ，如果短句子被成功翻译，则用句子结构节点替换对应于部分句子框的分词句，并且在搜索句框（205）的同时翻译所有句框，确定所有句子框是否成功 翻译（206），如果它们不是，则根据词组结构通过组合部分句子框来尝试翻译 分析规则（207），并检查部分句子翻译是否成功（208）。
-
公开(公告)号：KR100329109B1
公开(公告)日：2002-03-18
申请号：KR1019990033394
申请日：1999-08-13
Applicant: 한국전자통신연구원
IPC: G06F17/28
Abstract: 본발명은입력문장이가지는문맥정보와구문정보를모두활용하면서의미적으로자연스러운대역문을만들어내는프로텍터와구문노드를포함하는문틀을이용한자동번역기에관한것이다. 이러한프로텍터와구문노드를포함하는문틀을이용한자동번역기는, 입력되는원문을형태소단위로분석한후, 고정표현된형태소들에게는하나의품사를부여하고, 나머지각 형태소들에게는각각하나의품사를부여하는품사부여수단과; 상기품사부여된원문중에서중요한역할을하는품사들을프로텍터들로표시하고, 상기프로텍터들사이의부분구문들에는적절한구문태그를부착하는문장분석수단; 상기프로텍터들과부분구문들로생성된원문틀을원문틀데이터베이스에적용하여유사한데이터원문틀을찾는원문틀검색수단; 및상기원문틀에대응하는대역문틀들중 적절한하나의대역문틀을결정하여대역문을생성하는대역문생성수단을구비한다.
-
公开(公告)号：KR1020010063791A
公开(公告)日：2001-07-09
申请号：KR1019990061885
申请日：1999-12-24
Applicant: 한국전자통신연구원
IPC: G06F17/28
Abstract: PURPOSE: A device and method for deciding connection information of an English verbal phrase is provided to offer translating information with respect to a connection and creation of the English verbal phrase by a Korean language frame for deciding a connection pattern and a correct connecting pattern with respect to the end of a word. CONSTITUTION: A morpheme analyzer(101) performs an analyzing of a morpheme of the Korean language sentence to be translated. A sentence structure analyzer(102) performs a structure analysis as the unit of a verbal phrase using the analyzed information of the morpheme analyzer(101). A partial bilingual sentence connector(103) decides a connection relation between each verbal phrase, and selects the English language conjunction and decides a word order of verbal phrases to be translated and provides creating information using the analyzed Korean language information. A partial bilingual sentence generator(104) performs an English translation with respect to each verbal phrase as the unit of a short sentence. A bilingual sentence refiner(105) performs conforming of a sex, a number, and sequence of tenses and restores omitted components as the subject and a style correction process for creating an English sentence creation. A morpheme generator(106) creates the English morpheme.
Abstract translation: 目的：提供一种用于决定英语口头短语的连接信息的装置和方法，用于提供关于通过韩语语言连接和创建英语口头短语的翻译信息，用于确定连接模式和正确的连接模式 到一个字的结尾。 构成：语素分析器（101）对要翻译的韩语语句的语素进行分析。 句子结构分析器（102）使用语素分析器（101）的分析信息来执行结构分析作为语言短语的单位。 部分双语句连接器（103）决定每个口头短语之间的连接关系，并选择英语语言连接并决定要翻译的口头短语的单词顺序，并使用所分析的韩语信息提供创建信息。 部分双语句子发生器（104）以每个口头短语作为短句的单位执行英文翻译。 双语句子精炼器（105）执行性别，数量和时态序列的一致性，并且恢复省略的组件作为主题，以及用于创建英语句子创建的风格校正过程。 语素生成器（106）创建英语语素。
-
Patent Agency Ranking
-
公开(公告)号：KR101626386B1
公开(公告)日：2016-06-02
申请号：KR1020090123136
申请日：2009-12-11
Applicant: 한국전자통신연구원
Abstract: 본발명은자동번역시스템에서번역한번역문장내에나타나는번역오류를후처리보정장치를이용하여자동으로보정하여번역문장내의번역오류를수정함으로써번역품질을향상시키는번역오류후처리보정장치에관한것으로서, 특히목적언어코퍼스로부터번역오류보정을위한요소화언어모델을구축하고, 이에기반하여번역오류를탐색및 수정하는오류보정방법에관한것이다. 본발명은번역오류에대해후처리보정을함에있어서오류추정및 오류보정을위한기본지식으로사용되는요소화언어모델을구축하고이에기반하여단어신뢰도값을계산하고, 올바른오류보정성능을높임으로써, 오류가있는자동번역시스템의번역오류를수정하여보다높은품질의번역을수행할수 있다.
-
公开(公告)号：KR1020150092879A
公开(公告)日：2015-08-17
申请号：KR1020140013464
申请日：2014-02-06
Applicant: 한국전자통신연구원
CPC classification number: G06F17/273 , G06F17/271 , G06F17/2725 , G06F17/274
Abstract: Disclosed are an apparatus and a method for correcting grammatical errors in a hybrid method wherein a statistical method using n-gram data and a language analysis method are combined. According to an embodiment of the present invention, the method for correcting grammatical errors based on n-gram data and language analysis which is realized by a computer includes the steps of: tagging and pre-treating an input sentence; detecting a grammatical error candidate in the tagged and pre-treated input sentence by using n-gram statistical data extracted from a large amount of corpus; extracting a similar n-gram with respect to the grammatical error candidate and generating a corrected sentence by choosing final corrected n-gram using similarity, frequency, and grammatical conditions; receiving input of the corrected sentence again, analyzing phrases by applying error rules to the phrases, generating a phrase tree, and allocating node correction information to each node constituting the phrase tree; and correcting the corrected sentence by using the node correction information.
Abstract translation: 公开了一种混合方法中校正语法错误的装置和方法，其中组合使用n-gram数据和语言分析方法的统计方法。 根据本发明的实施例，根据由计算机实现的n-gram数据和语言分析来校正语法错误的方法包括以下步骤：对输入句子进行标记和预处理; 通过使用从大量语料库提取的n-gram统计数据来检测标记和预处理输入句中的语法错误候选; 提取相对于语法错误候选的类似的n-gram，并通过使用相似性，频率和语法条件选择最终校正的n-gram来产生校正句子; 再次接收更正的句子的输入，通过对短语应用错误规则来分析短语，生成短语树，并将节点校正信息分配给构成短语树的每个节点; 以及通过使用节点校正信息来校正校正后的句子。
-
公开(公告)号：KR1020150083153A
公开(公告)日：2015-07-17
申请号：KR1020140002176
申请日：2014-01-08
Applicant: 한국전자통신연구원
CPC classification number: G06F17/2755
Abstract: 본발명은형태소분석에관한것으로, 입력문을수신하는입력부, 상기입력문에대하여 N개(N은 1보다큰 자연수)의형태소분석모델을적용하고, 분석결과를결합하는제어부를포함하는언어형태소분석을지원하는것을특징으로하는전자장치의구성을개시한다.
Abstract translation: 本发明涉及语素分析。 根据本发明，公开了一种支持语素分析的电子设备的结构，其包括：输入部分，用于接收输入句子; 以及对输入句子应用N个语素分析模型（N为大于1的自然数）的控制部分，并结合分析结果。
-
公开(公告)号：KR1020150073715A
公开(公告)日：2015-07-01
申请号：KR1020130161729
申请日：2013-12-23
Applicant: 한국전자통신연구원
IPC: G06F17/27
CPC classification number: G06F17/2755
Abstract: 본발명의실시예에따른복합형태소분할장치는기분석패턴추출부, 복합형태소를입력으로받는입력부, 기분석패턴추출부에서추출된기분석패턴에기초하여복합형태소가기분석패턴과일치하는경우, 복합형태소를기분석패턴에따라형태소로분할하는기분석적용부, 기분석패턴추출부에서추출된기분석패턴에기초하여복합형태소가기분석패턴과일치하지않는경우복합형태소를내용형태소와복합기능형태소로분할하는제1 분할부및 복합기능형태소를기분석패턴추출부에서추출된기분석패턴에기초하여형태소로분할하는제2 분할부를포함한다.
Abstract translation: 本发明涉及一种用于分割复合语素的装置，包括：预分析图案提取单元; 接收复合语素作为输入的输入单元; 一种预先分析的应用单元，当复合语素基于预分析模式提取单元提取的预分析模式匹配预分析模式时，根据预分析模式将复合语素分解为语素; 当复合词素与预先分析的图案提取单元提取的预分析图案不一致时，将复合词素分为物质词素和复合函数语素的第一分割单元; 以及第二分割单元，其基于通过预分析图案提取单元提取的预分析图案将复合函数语素划分为语素。
-
-
-
-
-
-
-
-
-
Search Results
211
records
(took 0.022 seconds)
