公开(公告)号：KR100407696B1

公开(公告)日：2003-12-01

申请号：KR1019990021549

申请日：1999-06-10

Applicant: 한국전자통신연구원

Inventor： 장명길 ,  박세영 ,  정경택

IPC: G06F17/30

Abstract: PURPOSE: A retrieval performance measurement method for a key fact based text retrieval model is provided to calculate a weight value on a document and a query language and give the document a priority based on a similarity between the document and the query. CONSTITUTION: A retrieval performance measurement method for a key fact based text retrieval model comprises the steps of extracting key words from a set of documents and queries(S01), asking if setting a variable value of retrieval performance assessment elements on the extracted result(S02), if the answer is positive, giving the variable value of retrieval performance assessment elements on a new document size, a key fact frequency within the document, and a key fact weight constant(S03), making a document and a query vector including the assessment variable value(S04), calculating a key fact weight value of the document and the query by a key fact weight equation(S05), obtaining a retrieval performance result of the key fact based text retrieval model for searching for an optimal retrieval model according to characteristics of a retrieval target document domain(S06), giving the documents a priority number(S07), and assessing the retrieval model(S08).

Abstract translation: 目的：提供一种基于关键事实的文本检索模型的检索性能度量方法，用于计算文档和查询语言的权重值，并基于文档和查询之间的相似性为文档赋予优先级。 构成：基于关键事实的文本检索模型的检索性能测量方法包括以下步骤：从一组文档和查询中提取关键字（S01），询问是否在提取的结果（S02）上设置可变值检索性能评估元素 ），如果答案是肯定的，则在新的文档大小，文档内的关键事实频率和关键事实权重常数（S03）上给出检索性能评估元素的变量值，使文档和查询向量包括 评估变量值（S04），通过关键事实权重方程（S05）计算文档和查询的关键事实权重值，获得基于关键事实的文本检索模型的检索性能结果，以根据关键事实权重方程搜索最优检索模型 到检索对象文档域的特征（S06），给出文档优先权编号（S07）以及评估检索模型（S08）。

公开(公告)号：KR100399582B1

公开(公告)日：2003-09-26

申请号：KR1019990038535

申请日：1999-09-10

Applicant: 한국전자통신연구원

Inventor： 김영길 ,  김태완 ,  최승권 ,  여상화 ,  정한민 ,  심철민 ,  박상규 ,  박세영

IPC: G06F17/27

Abstract: PURPOSE: A Korean sentence structure analyzer is provided to separate a long sentence to interpret by separately processing a long sentence in a prior sentence structure analysis stage. CONSTITUTION: A Korean morpheme interpreting device(1) analyzes the inputted Korean sentence if a Korean sentence is inputted. A morpheme paragraph number detecting device(2) decides the paragraph number of an analyzed morpheme. At this time, if the paragraph number is more than a critical value, the inputted Korean sentence is decided as a long sentence. A relaxation device(3) separates a long Korean sentence into short sentences. A Korean sentence structure interpreting device(4) performs a sentence structure analysis with respect to each short sentence, respectively. The result of sentence structure analysis creates each Korean sentence structure interpretation tree. A Korean sentence structure interpretation tree combination device(5) combines the analyzed interpretation tree, and creates one analytic tree.

Abstract translation: 目的：提供韩语句子结构分析器，通过在早期句子结构分析阶段中分开处理长句来分离长句以进行解释。 一种韩语语素解释装置（1），如果输入韩文句子，则分析输入的韩语句子。 词素段落号码检测装置（2）决定分析后的词素的段落号码。 此时，如果段落号超过临界值，则输入的韩语句子被判定为长句。 放松装置（3）将长篇韩文句子分成短句。 韩语句子结构解释装置（4）分别针对每个短句执行句子结构分析。 句子结构分析的结果创建了每个韩语句子结构解释树。 韩语句子结构解释树组合装置（5）组合分析的解释树，并创建一个分析树。

公开(公告)号：KR100385863B1

公开(公告)日：2003-06-02

申请号：KR1019990016791

申请日：1999-05-11

Applicant: 한국전자통신연구원

Inventor： 장명길 ,  박세영 ,  맹성현

IPC: G06F17/30

Abstract: PURPOSE: A Korean-English query conversion method using inter-information and an apparatus thereof are provided for generating a high quality inquiry language by adapting an inter-information to multiple processes of a conversion operation. CONSTITUTION: An inquiry language conversion apparatus using an inter-information includes a keyword extractor(11), a dictionary based inquiry language converter(12), a band language ambiguity overcoming unit(13), an inquiry language word weight providing unit(14), and a band dictionary(15). The keyword extractor(11) extracts a keyword for a search based on a type analysis and a part of a speech tagging with respect to an inquiry language of an original language.

Abstract translation: 目的：提供一种利用信息间的韩 - 英查询转换方法及其装置，用于通过使信息间适应转换操作的多个过程来生成高质量的查询语言。 （11），一个基于字典的查询语言转换器（12），一个频带语言歧义克服单元（13），一个查询语言字权重提供单元（14），一个查询语言字权重提供单元 和带字典（15）。 关键字提取器（11）针对原始语言的查询语言，基于类型分析和语音标注的一部分，提取搜索关键词。

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

Inventor： 정한민 ,  김태완 ,  심철민 ,  최승권 ,  여상화 ,  김영길 ,  류병래 ,  서광준 ,  서영애 ,  박상규 ,  박세영 ,  노윤형

IPC: G06F17/28

Abstract: 본발명은입력문장이가지는문맥정보와구문정보를모두활용하면서의미적으로자연스러운대역문을만들어내는프로텍터와구문노드를포함하는문틀을이용한자동번역기에관한것이다. 이러한프로텍터와구문노드를포함하는문틀을이용한자동번역기는, 입력되는원문을형태소단위로분석한후, 고정표현된형태소들에게는하나의품사를부여하고, 나머지각 형태소들에게는각각하나의품사를부여하는품사부여수단과; 상기품사부여된원문중에서중요한역할을하는품사들을프로텍터들로표시하고, 상기프로텍터들사이의부분구문들에는적절한구문태그를부착하는문장분석수단; 상기프로텍터들과부분구문들로생성된원문틀을원문틀데이터베이스에적용하여유사한데이터원문틀을찾는원문틀검색수단; 및상기원문틀에대응하는대역문틀들중 적절한하나의대역문틀을결정하여대역문을생성하는대역문생성수단을구비한다.

公开(公告)号：KR100305587B1

公开(公告)日：2001-09-28

申请号：KR1019970071084

申请日：1997-12-19

Applicant: 한국전자통신연구원

Inventor： 정경택 ,  최동시 ,  서래원 ,  전미선 ,  박세영

IPC: G06F17/30

Abstract: PURPOSE: A method for searching a related noun for searching information is provided to enhance a reproducing rate of a search and interpret a word clearly by applying a relation noun automatically extracting algorithm from a large quantity of corpus and performing a query language extension through an automatically constructed relation noun dictionary. CONSTITUTION: It is checked whether a postposition of a word to be searched in a sentence is a connection postposition or not(303). If the postposition is a connection postposition, the next word is appended(304), and the stage is returned to the above (303) stage. If the postposition is not a connection postposition, it is checked whether the word is connected to a rest symbol or not(305). If the word is connected to a rest symbol, it is checked whether a noun is connected to a rest symbol(307). If the word is not connected to a rest symbol, it is checked whether the next word is a connection word(308). If the word is not connected to a noun and a rest symbol, the process is terminated. If the word is connected to a noun and a rest symbol, the next word is appended(304), and the stage is returned to the above (303) stage. If the word is not a connection word, the process is terminated. If the word is a connection word, the next word is appended(304), and the stage is returned to the above (303) stage.

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

Inventor： 서영애 ,  김태완 ,  김영길 ,  서광준 ,  심철민 ,  여상화 ,  정한민 ,  최승권 ,  박상규 ,  박세영

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。

公开(公告)号：KR1020010026990A

公开(公告)日：2001-04-06

申请号：KR1019990038535

申请日：1999-09-10

Applicant: 한국전자통신연구원

Inventor： 김영길 ,  김태완 ,  최승권 ,  여상화 ,  정한민 ,  심철민 ,  박상규 ,  박세영

IPC: G06F17/27

Abstract: PURPOSE: A Korean sentence structure analyzer is provided to separate a long sentence to interpret by separately processing a long sentence in a prior sentence structure analysis stage. CONSTITUTION: A Korean morpheme interpreting device(1) analyzes the inputted Korean sentence if a Korean sentence is inputted. A morpheme paragraph number detecting device(2) decides the paragraph number of an analyzed morpheme. At this time, if the paragraph number is more than a critical value, the inputted Korean sentence is decided as a long sentence. A relaxation device(3) separates a long Korean sentence into short sentences. A Korean sentence structure interpreting device(4) performs a sentence structure analysis with respect to each short sentence, respectively. The result of sentence structure analysis creates each Korean sentence structure interpretation tree. A Korean sentence structure interpretation tree combination device(5) combines the analyzed interpretation tree, and creates one analytic tree.

Abstract translation: 目的：提供韩语句子结构分析器，通过在先前句子结构分析阶段分开处理长句来分离长句来解释。 规定：韩国语素解释装置（1）如果输入韩语句子，则分析输入的韩语句子。 语素段号码检测装置（2）决定分析语素的段号。 此时，如果段数超过临界值，则输入的韩语句子被判定为长句。 放松装置（3）将长期的韩语句子分成短句。 韩国句子结构解释装置（4）分别对每个短句执行句子结构分析。 句子结构分析的结果创建了每个韩语句子结构解释树。 韩国句子结构解释树组合设备（5）结合分析的解释树，并创建一个分析树。

公开(公告)号：KR1020000039748A

公开(公告)日：2000-07-05

申请号：KR1019980055170

申请日：1998-12-15

Applicant: 한국전자통신연구원

Inventor： 심철민 ,  김태완 ,  최승권 ,  여상화 ,  김영길 ,  정한민 ,  박상규 ,  박세영

IPC: G06F17/28

Abstract: PURPOSE: An apparatus for translating web documents written in multi-languages and a method for a translating service using the apparatus is provided to navigate the web using a native language by automatically translating various foreign language on the web documents into the native language. CONSTITUTION: A hyper-text transfer protocol(HTTP) server(11) connects a user to an automatic translation device(17) through a web. The automatic translation device(17) is operated by the HTTP server(11) while the user is connected to the HTTP server(11) to perform a translation. A translation control device(12) manages a proxy control device(14) and processes a translating object document as a translating shape. A proxy server(13) receives an original document by the translation control device(12), stores and manages a translated result document, and transmits the translation object document quickly. A proxy control device(14) controls an operation of the proxy server(13), and is interlocked with the translation control device(12). An additional function device(15) provides an additional function such as a general document translation function and a meta search function. A language recognizing device(16) analyzes the original document to recognize a language by a document, a paragraph and a composition, accesses a corresponding translation device and collects a translated result. A multi-language automatic translation device(17) performs a translation according to a pair of languages.

Abstract translation: 目的：提供一种用于翻译以多语言编写的网络文档的装置以及使用该装置的翻译服务的方法，以通过将web文档上的各种外语自动翻译成母语来使用母语来浏览网页。 构成：超文本传输​​协议（HTTP）服务器（11）通过网络将用户连接到自动翻译设备（17）。 自动翻译装置（17）由HTTP服务器（11）操作，同时用户连接到HTTP服务器（11）以进行翻译。 翻译控制装置（12）管理代理控制装置（14）并且将翻译对象文档作为平移形状进行处理。 代理服务器（13）由翻译控制装置（12）接收原始文档，存储和管理翻译的结果文档，并快速传送翻译对象文档。 代理控制装置（14）控制代理服务器（13）的操作，并且与翻译控制装置（12）互锁。 另外的功能设备（15）提供诸如通用文档翻译功能和元搜索功能的附加功能。 语言识别装置（16）通过文档，段落和构图分析原始文档以识别语言，访问相应的翻译装置并收集翻译结果。 多语言自动翻译装置（17）根据一对语言执行翻译。

公开(公告)号：KR100250442B1

公开(公告)日：2000-04-01

申请号：KR1019970072058

申请日：1997-12-22

Applicant: 한국전자통신연구원

Inventor： 강현규 ,  박세영

IPC: G06F17/28

Abstract: PURPOSE: The method for solving the ambiguity of words in searching the natural language information is provided to improve the efficiency of the information search by offering the ordered searching result through the second arrangement between the neighbor word and the first word after searching the first natural language through the keyword index. CONSTITUTION: The method comprises the following steps. The first natural language searching document list is inputted in the procedure of ordering the document(301). Checks if the inputted first natural language searching document is the last concerned to the next document(302). If yes, the document is rearranged by the weight value of each document and the process exits(303). If no, the similarity calculation between the query and the document is made(304). After storing the similarity value between the query and the document(305), it is checked if the inputted document is the last concerned to the next document.

Abstract translation: 目的：提供搜索自然语言信息中词语歧义的方法，通过在搜索第一个自然语言之后，通过相邻单词和第一个单词之间的第二个排列提供有序搜索结果来提高信息搜索的效率 通过关键字索引。 规定：该方法包括以下步骤。 在订购文档（301）的过程中输入第一自然语言搜索文档列表。 检查输入的第一自然语言搜索文档是否是下一个文档的最后一个（302）。 如果是，则文档按每个文档的权重值重新排列，并且进程退出（303）。 如果否，则查询和文档之间的相似度计算（304）。 在存储查询和文档（305）之间的相似性值之后，检查输入的文档是否是下一个文档的最后一个。

公开(公告)号：KR1019980047276A

公开(公告)日：1998-09-15

申请号：KR1019960065752

申请日：1996-12-14

Applicant: 한국전자통신연구원

Inventor： 정경택 ,  최동시 ,  박세영

IPC: G06F3/14

Abstract: 본 발명은 3차원 모델링 및 애니메이션, 가상 현실, 방송, 가상 스튜디오, 영화, 그리고 문서 작성 등에서 효과적인 3차원 폰트를 손쉽게 지원하기 위하여, 도우즈의 트루 타입 폰트로부터 3차원 폰트를 자동 생성할 수 있는 3차원 폰트 생성 기법과, 상기 3차원 폰트 생성 기법을 이용하여 여러 글꼴의 3차원 폰트 데이타 세트를 생성할 수 있는 3차원 한글/한자 폰트 제작을 위한 3차원 폰트 생성 기법에 관해 개시된다.