公开(公告)号：KR100921563B1

公开(公告)日：2009-10-12

申请号：KR1020080038708

申请日：2008-04-25

Applicant: 한국과학기술원

Inventor： 최기선 ,  최동현

IPC: G06F17/27

CPC classification number: G06F17/2785

Abstract: PURPOSE: A method of sentence compression using a dependency grammar parse tree is provided to improve the readability and to improve the abstract efficiency of a document. CONSTITUTION: The method of sentence compression using a dependency grammar parse tree comprises as follows. The first dependency grammar parse tree is produced by the syntax analyzer of regulation base. If there are words which the fist dependency grammar parse tree can't find. The second dependency grammar parse tree is produced by the dependency grammar analyzer of probability base. The third dependency grammar parse tree is produced by combining the first dependency grammar parse tree with the second. The fourth dependency grammar is produced by an artificial intelligence model using 'CHILD_UP' and 'REMAIN', 'DELETE' operation.

Abstract translation: 目的：提供使用依赖语法解析树的句子压缩方法，以提高可读性并提高文档的抽象效率。 构成：使用依赖语法解析树的句子压缩方法如下。 第一个依赖语法解析树由规则库的语法分析器生成。 如果有第一个依赖语法解析树找不到的话。 第二个依赖语法解析树是由概率基础的依赖语法分析器产生的。 第三个依赖语法解析树是通过将第一个依赖关系语法解析树与第二个依赖语法解析树组合而产生的。 第四个依赖语法是由使用“CHILD_UP”和“REMAIN”，“DELETE”操作的人造智能模型产生的。

公开(公告)号：KR1020100047475A

公开(公告)日：2010-05-10

申请号：KR1020080106383

申请日：2008-10-29

Applicant: 한국과학기술원

Inventor： 최기선 ,  최동현

IPC: G06F17/26 ,  G06F17/27 ,  G06F17/30

CPC classification number: G06F17/279

Abstract: PURPOSE: An automatic relation triplets extraction method through a search of a dependency grammar sentence tree is provided to reduce time and cost highly by automating a suitable part of an ontology construction from a general sentence. CONSTITUTION: A sentence structure of a target sentence is analyzed. A dependency grammar sentence tree is created using the analysis. A pre-processing of the dependency grammar sentence tree is operated. The dependency grammar sentence tree is transformed to a form for relation extraction. The converted dependency grammar sentence tree is searched in a post order method. A relation triplets are automatically extracted using the search.

Abstract translation: 目的：提供一种通过搜索依赖语法句子树的自动关联三元组提取方法，通过从一般句子自动化本体构造的适当部分来高效地减少时间和成本。 构成：分析目标句子的句子结构。 使用分析创建依赖语法句子树。 操作依赖语法句树的预处理。 依赖语法句子树被转换为关系提取的形式。 转换的依赖关系语法句子树以后期方法进行搜索。 使用搜索自动提取关系三元组。

公开(公告)号：KR100916645B1

公开(公告)日：2009-09-08

申请号：KR1020080038707

申请日：2008-04-25

Applicant: 한국과학기술원

Inventor： 최기선 ,  최동현

IPC: G06F17/27

CPC classification number: G06F17/277 ,  G06F17/227 ,  G06F17/274

Abstract: A method of sentence compression using lexical information, principal grammar element, and title information is provided to improve readability and summarization efficiency for abstracting a document. A title of a document and sentences are inputted(S10). A syntactic analysis tree is generated by a Top-Down mode(S20). A primary grammar element is extracted and indicated(S30). A decision tree is used to determine whether an initial word of a current sentence is included in a summarized sentence(S40). Lexical information is used to indicate the initial word in the syntactic analysis tree as a main part(S50). In case words do not exist in a current sentence, the current sentence is summarized(S60,S70).

Abstract translation: 提供了一种使用词汇信息，主语法元素和标题信息进行句子压缩的方法，以提高文档抽象的可读性和总结效率。 输入文件的标题（S10）。 语法分析树通过自顶向下模式生成（S20）。 提取并指示主语法元素（S30）。 决策树用于确定当前句子的初始词是否包括在总结句中（S40）。 词法信息用于将语法分析树中的初始词指示为主要部分（S50）。 如果当前句子中不存在字，则总结当前句子（S60，S70）。

公开(公告)号：KR1020140097701A

公开(公告)日：2014-08-07

申请号：KR1020130009773

申请日：2013-01-29

Applicant: 한국과학기술원

Inventor： 최기선 ,  최동현 ,  김경렬 ,  김은경

IPC: G06F17/00 ,  G06F17/20 ,  G06F17/27

CPC classification number: G06F17/2705 ,  G06F17/30241

Abstract: The present invention relates to a method and system for looking for the geographic location of a place expressed by a text object. The method for looking for the geographic location of the place expressed by the text object according to the embodiment of the present invention includes the steps of: constructing an LGG; obtaining a finite-state transducer from the LGG; and obtaining a geo-code using the transducer.

Abstract translation: 本发明涉及一种用于查找由文本对象表示的地点的地理位置的方法和系统。 根据本发明实施例的用于查找由文本对象表示的地点的地理位置的方法包括以下步骤：构建LGG; 从LGG获得有限状态传感器; 并使用换能器获得地理代码。

公开(公告)号：KR101404206B1

公开(公告)日：2014-06-05

申请号：KR1020130009752

申请日：2013-01-29

Applicant: 한국과학기술원

Inventor： 최기선 ,  최동현

IPC: G06F17/20

CPC classification number: G06F17/2705 ,  G06Q50/01 ,  G06Q50/32

Abstract: The present invention relates to a method for extracting time information in Korean texts and a time information extraction system thereof, and more specifically, to the method which can express the relationship between the time information and the context to automatically identify and extract the time information included in a gathering notification written in Korean such as the starting time and end time of the gathering and an information extraction system thereof. The time information extraction method according to an embodiment of the present invention uses a support vector machine.

Abstract translation: 本发明涉及一种用于提取韩文文本中的时间信息的方法及其时间信息提取系统，更具体地，涉及可以表达时间信息与上下文之间的关系的方法，以便自动识别和提取包括的时间信息 在韩语中采集的收集通知，如收集的开始时间和结束时间以及信息提取系统。 根据本发明实施例的时间信息提取方法使用支持向量机。