• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.11a
• /
• pp.593-596
• /
• 2002

정보추출이란 자연어로 작성된 문서 집합에서 원하는 정보를 선택하여 구조화된 표현으로 생성하는 것을 말한다. 문장 단위로 정보 추출 작업을 수행할 때 추출되는 정보를 보유한 문장을 이벤트 문장이라고 정의하고 이러한 이벤트 문장의 구조를 분석하여 최종적으로 유용한 정보를 추출하기 위해서는 이벤트 문장의 구조를 파악하기 위해 이벤트 문장을 단문으로 분할하여 구조를 분석한다. 본 연구에서는 단문 구조 분석을 위해 일반적인 한국어 문장의 특성과 용언의 조사 정보를 이용하고 이러한 정보로 분석할 수 없는 문장에 대해서는 공기 정보를 사용한다. 사용되는 공기 정보는 개체명이 많이 사용되는 이벤트 문장의 특성을 이용하기 위하여 개체명으로 확장된 명사(개체명)-조사-용언의 공기 정보를 구축하여 사용한다. 개체명 확장된 공기 정보는 일반 공기 정보에 비해 이벤트 문장에서 F-Measure 기준으로 약 2%의 성능향상을 보인다.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.43 no.6
• /
• pp.187-196
• /
• 2001

In this study, by using the natural language processing of the field of artificial intelligence, automated index was performed. And then, the Natural Language Processing Interface for knowledge representation(NALPI) has been developed. Furthermore, the DEsign KnOwledge DataBase(DEKODB) has been also developed, which is designed to interlock the knowledge base. The DEKODB processes both the documented design-data, like a concrete standard specification, and the design knowledge from an expert. The DEKODB is also simulates the design space of structures accordance with the production rule, and thus it is determined that DEKODB can be used as a engine to retrieve new knowledge and to implement knowledge base that is necessary to the development of automatic design system. The application field of the system, which has been developed in this study, can be expanded by supplement of the design knowledge at DEKODB and developing dictionaries for foreign languages. Furthermore, the perfect automation at the data accumulation and development of the automatic rule generator should benefit the unified design automation.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.5
• /
• pp.1434-1445
• /
• 2000

An expert system executes the inference, based on the knowledge of specific domain. the reliability on the results of inference depends upon both the consistency and accuracy of knowledge. This is the reason why expert system requires the facilities which can practice an access to the various kinds of knowledge and maintain the consistency and accuracy of knowledge an maintain the consistency and accuracy of knowledge. This paper is to implement an expert system permitting an access of declarative and procedural knowledge in the knowledge base and in the data base. This paper is also to implement a knowledge acquisition system which adds the knowledge a only if its accuracy and consistency are maintained, after verifying the potential errors such as contradiction, redundancy, circulation, non-reachable rule and non-lined rule. In consequence, the expert system realizes a good access to the various sorts of knowledge and increases the reliability on the results of inference. The knowledge acquisition system contributes tro strengthening man-machine interface that enables users to add the knowledge easily to the knowledge base.

• International Journal of CAD/CAM
• /
• v.5 no.1
• /
• pp.83-90
• /
• 2005

This is a report on a new methodology to manage design knowledge by utilizing a knowledge-based CAD and a prototype system named $C^3$ (Cubic; CAD knowledge Code Capacitor), which is being developed using our methodology. $C^3$ facilitates (i) the automatic generation of a knowledge code for a knowledge-based CAD by processing design documents written in the format near the natural language, such as English or Japanese, and (ii) automatically generation of a design document written in the format near the natural language from the knowledge code. The features of the system facilitate document-based design knowledge management which reduces the designer's load to encode and maintain design knowledge, because it is easier for a designer to treat a natural language description than a coded description.

• Annual Conference on Human and Language Technology
• /
• 2002.10e
• /
• pp.325-331
• /
• 2002

정보추출 시스템의 목적은 관심의 대상이 되는 특정 정보를 선택적으로 찾아내 제시하는데 있다. 따라서 도메인 정보에 의존적인 방법으로 정보추출이 이루어질 수밖에 없고, 이에 따른 도메인 정보 구축의 부담이 컸다. 이러한 부담을 줄이기 위해 본 연구에서는 특정 주제영역과 관련한 문서로부터 자동으로 이벤트 문장을 추출하는 시스템을 제안한다. 이벤트 문장이란, 특정도메인에서 다루어지는 이벤트의 구체적인 내용을 포함하고 있는 문장이다. 이러한 문장을 추출함으로써 기본적인 수준의 정보추출 요구를 만족시킬 수 있을 뿐만 아니라, 주출된 이벤트 문장을 도메인 정보 구축에 활용할 수 있을 것이다. 본 연구에서는 동사, 명사, 명사구, 및 3W 자질을 이용하여 문장추출의 성능을 최대화하기 위한 방안을 제안하고, 세 개의 평가 도메인을 대상으로 실험을 수행하였다. 실험 결과, when 및 where 자질과 동사, 명사. 명사구의 가중치를 이용하여 문장 가중치를 계산함으로써 최적의 이벤트 문장추출 성능을 얻을 수 있음을 알 수 있었다.

• Journal of The Korean Association For Science Education
• /
• v.38 no.5
• /
• pp.693-703
• /
• 2018

One of the important competencies in knowledge and information society is the competency of Knowledge information processing. This is closely related to science education and described as one of the core competencies in the 2015 national curriculum revision. Even with a general agreement of the educational necessity of this competency, its practice in class depends mostly on teachers' will. Therefore, we surveyed science teachers' perceptions and classroom condition about the competency of Knowledge information processing, and we analyzed the questionnaires of 64 middle and high school teachers in Seoul and interviewed three teachers. As a result, all teachers shared the importance of Knowledge information processing competency and explained it in terms of social paradigm and goal of the subject. However, there were not many cases of actual practice in class. The teachers answered that time for Knowledge information processing competency is not enough in class and they also lack of PCK on this competency. About half of the teachers had experiences in teacher training about Knowledge information processing competency but most of their experiences are related to information utilization literacy. The importance of Knowledge information processing competency was very high in three factors (collection, analyzation, and utilization), among which information analysis was the highest. Middle school teachers showed higher scores in most questions even though the differences were not significant, and high school teachers showed higher scores in the importance of information sources at a significant level. In order to cultivate competencies, it is necessary to expand the meaning of science inquiry so as to cover this competency and to consider ways of linking with other subjects and develop methods of teaching and learning.

• Healthcare Informatics Research
• /
• v.24 no.4
• /
• pp.376-380
• /
• 2018

Objectives: This research presents the design and development of a software architecture using natural language processing tools and the use of an ontology of knowledge as a knowledge base. Methods: The software extracts, manages and represents the knowledge of a text in natural language. A corpus of more than 200 medical domain documents from the general medicine and palliative care areas was validated, demonstrating relevant knowledge elements for physicians. Results: Indicators for precision, recall and F-measure were applied. An ontology was created called the knowledge elements of the medical domain to manipulate patient information, which can be read or accessed from any other software platform. Conclusions: The developed software architecture extracts the medical knowledge of the clinical histories of patients from two different corpora. The architecture was validated using the metrics of information extraction systems.

• Journal of Information Processing Systems
• /
• v.5 no.1
• /
• pp.11-18
• /
• 2009

As well as providing various APIs for the development of inference engines and storage models, Jena is widely used in the development of systems or tools related with Web ontology management. However, Jena still has several problems with regard to the development of real applications, one of the most important being that its query processing performance is unacceptable. This paper proposes a storage model to improve the query processing performance of the original Jena storage. The proposed storage model semantically classifies OWL elements, and stores an ontology in separately classified tables according to the classification. In particular, the hierarchical knowledge is managed, which can make the processing performance of inferable queries enhanced and stores information. It enhances the query processing performance by using hierarchical knowledge. For this paper an experimental evaluation was conducted, the results of which showed that the proposed storage model provides a improved performance compared with Jena.

• Knowledge Management Research
• /
• v.15 no.4
• /
• pp.105-126
• /
• 2014

Knowledge integration is becoming a primary function of improving organizational capabilities and performance in today's convergence paradigm. The knowledge integration capability of employees has increasingly been regarded as a critical source for developing new products and services. This study investigates the influential factors of employees' knowledge integration capability and its effects. A theoretical research model was developed based on the socio-technical perspective and information processing theory. The model includes teamwork quality, expertise, IT support, and knowledge complexity as the primary influential factors of employees' knowledge integration capability. A large-scale survey was conducted for gathering data (a total of 316 samples from 141 organizations) to test the proposed model. The test results of the hypotheses show that expertise and knowledge complexity are the significant influential factors of employees' knowledge integration capability, and also the capability has a positive effect on the knowledge creation performance of employees. Our findings contribute to the development of initiatives for promoting employees' knowledge integration capability, especially in knowledge intensive organizations focusing on convergence products and services.

• Annual Conference on Human and Language Technology
• /
• 2000.10d
• /
• pp.323-328
• /
• 2000

국내에서 영한 자동번역 시스템을 1985 년부터 개발한 지 벌써 15년이 흐르고 있다. 15 년의 영한 자동번역 기술개발에도 불구하고 아직도 영한 자동번역 시스템의 번역품질은 40%를 넘지 못하고 있다. 이렇게 번역품질이 낮은 이유는 다음과 같이 요약할 수 있을 것이다. o 입력문에 대해 파싱할 때 오른쪽 경계를 잘못 인식함으로써 구조적 모호성의 발생문제: 예를 들어 등위 접속절에서 오른쪽 등위절이 등위 접속절에 포함되는 지의 모호성. o 번역 단위로써 전체 문장을 대상으로 한 번역패턴이 아닌 구나 절과 같은 부분적인 번역패턴으로 인한 문장 전체의 잘못된 번역 결과 발생. o 점차 증가하는 대용량 번역지식의 구축과 관련해 새로 구축되는 번역 지식과 기구축된 대용량 번역지식들 간의 상호 충돌로 인한 번역 품질의 저하. 이러한 심각한 원인들을 극복하기 위해 본 논문에서는 문틀에 기반한 새로운 영한 자동번역 방법론을 소개하고자 한다. 이 문틀에 기반한 영한 자동번역 방법론은 현재 CNN뉴스 방송 자막을 대상으로 한 영한 자동번역 시스템에서 실제 활용되고 있다. 이 방법론은 기본적으로 data-driven 방법론에 속하다. 문틀 기반 자동번역 방법론은 규칙기반 자동번역 방법론보다는 낮은 단계에서 예제 기반 자동번역 방법론보다는 높은 단계에서 번역을 하는 번역방법론이다. 이 방법론은 영한 자동번역에 뿐만 아니라 다른 언어쌍에서의 번역에도 적용할 수 있을 것이다.