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:
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:
PURPOSE: A system and a method of an electronic-memo based on a machine-processable knowledge structure are provided to improve the interference ability of a system by indicating the information, which is inferred through an electronic memo network browser, in right and wrong answers. CONSTITUTION: An electronic memo pad(4) indicates a picture or writing, and transmits the contents of the drawing and writing to an electronic device and a communication network. An electronic memo input unit(5) inputs the contents, and an electronic memo service unit(2) creates a triplet of an RDF(Resource Description Framework) type from the contents of the electronic memo. Based on machine-processable knowledge structure, the electronic memo service device creates new information. The new information is inferred from the triplet.
Abstract:
PURPOSE: A relation construction device between ontology classes and a method thereof are provided to remove the restriction caused by the pattern base class relation setting by setting the relations between ontology classes of the specialized terminology through the syntax analysis. CONSTITUTION: A terminology selector(10) selects the specialized terminology in the specialized terminology domain. A sentence collector(20) collects the sentence including the specialized terminology. A syntax analyzer(30) analyzes grammatical relations between the specialized terminology and other sentence components. An extraction tool(40) reflects the syntax analyzed result and extracts the different specialized terminology from the description predicate included in the sentence. A specialized terminology adding module(50) adds the different specialized terminology to the specialized terminology ontology.
Abstract:
PURPOSE: A system for searching a Korean full text information in a computer system is provided to increase the efficiency of a run-length encoding in position information of each paragraph by using a relative position value in case that the position information is stored. CONSTITUTION: A professional index sets the unit of an index word as the unit of a paragraph unit. In case of the English-speaking world, a paragraph equals to the unit of a word. A prototype is restored by Stemizing method. In case that it isn't easy to change a word as the English, an index is compiled by a prototype according to a fixed rule. Therefore, the whole number of index words is reduced. In case of an inflected language as the Korean, a prototype is restored by a morpheme analysis. Various results are extracted. Therefore, one is selected among the results by a tagger or a fixed rule.
Abstract:
본 발명은 원문으로부터 다른 언어로의 번역문을 생성시키는 기계번역(machine translation) 시스템에 관한 것으로서, 보다 상세하게는 기계 번역의 과정에 있어서 원문 문서의 복잡도에 따라 그 원문이 요구하는 분석 수준에 따라서 다양한 번역 방식 즉, 형태소 분석, 구문 분석, 의미소 분석 등을 융통성 있게 실행하기 위하여, 다양한 수준의 분석 변환을 하는 분석(analysis) 모듈(10,20,30)과, 상기 분석 모듈들이 출력하는 변환 문서를 평가하는 평가자(evaluator)와, 상기 분석 모듈에 대응하며 상기 평가자를 포함하는 생성(generator) 모듈(50,60,70) 그리고 상기 평가자가 변환 문서를 받아들일 수 없을 때에 상기 분석 모듈로 피드백 되는 정보를 저장하는 번역 메모리(40)로 이루어지는 기계번역 시스템에 관한 것이다.
Abstract:
URI 정의문및 부가정보기반텍스트에서개체의 URI를식별하는장치, 토픽분포추정방법및 URI 선택방법이개시된다. 여기서, 장치는모든 URI(Uniform Resource Identifier)에대한정의문및 부가정보로구성된 URI 문서집합에대하여추정된토픽분포로부터개별 URI 문서의토픽분포를생성하는토픽분포추정부, 그리고 URI 식별대상인개체표면형을포함한질의텍스트가입력되면, 상기질의텍스트로부터상기개체표면형을추출하고, 상기질의텍스트의토픽분포를추정하며, 상기토픽분포를기초로상기개체표면형에해당하는 URI를선택하는 URI 선택부를포함한다.