지식베이스 구축을 위한 한국어 위키피디아의 학습 기반 지식추출 방법론 및 플랫폼 연구

김재헌,이명진 한국지능정보시스템학회 2019 지능정보연구 Vol.25 No.1

Development of technologies in artificial intelligence has been rapidly increasing with the Fourth Industrial Revolution, and researches related to AI have been actively conducted in a variety of fields such as autonomous vehicles, natural language processing, and robotics. These researches have been focused on solving cognitive problems such as learning and problem solving related to human intelligence from the 1950s. The field of artificial intelligence has achieved more technological advance than ever, due to recent interest in technology and research on various algorithms. The knowledge-based system is a sub-domain of artificial intelligence, and it aims to enable artificial intelligence agents to make decisions by using machine-readable and processible knowledge constructed from complex and informal human knowledge and rules in various fields. A knowledge base is used to optimize information collection, organization, and retrieval, and recently it is used with statistical artificial intelligence such as machine learning. Recently, the purpose of the knowledge base is to express, publish, and share knowledge on the web by describing and connecting web resources such as pages and data. These knowledge bases are used for intelligent processing in various fields of artificial intelligence such as question answering system of the smart speaker. However, building a useful knowledge base is a time-consuming task and still requires a lot of effort of the experts. In recent years, many kinds of research and technologies of knowledge based artificial intelligence use DBpedia that is one of the biggest knowledge base aiming to extract structured content from the various information of Wikipedia. DBpedia contains various information extracted from Wikipedia such as a title, categories, and links, but the most useful knowledge is from infobox of Wikipedia that presents a summary of some unifying aspect created by users. These knowledge are created by the mapping rule between infobox structures and DBpedia ontology schema defined in DBpedia Extraction Framework. In this way, DBpedia can expect high reliability in terms of accuracy of knowledge by using the method of generating knowledge from semi-structured infobox data created by users. However, since only about 50% of all wiki pages contain infobox in Korean Wikipedia, DBpedia has limitations in term of knowledge scalability. This paper proposes a method to extract knowledge from text documents according to the ontology schema using machine learning. In order to demonstrate the appropriateness of this method, we explain a knowledge extraction model according to the DBpedia ontology schema by learning Wikipedia infoboxes. Our knowledge extraction model consists of three steps, document classification as ontology classes, proper sentence classification to extract triples, and value selection and transformation into RDF triple structure. The structure of Wikipedia infobox are defined as infobox templates that provide standardized information across related articles, and DBpedia ontology schema can be mapped these infobox templates. Based on these mapping relations, we classify the input document according to infobox categories which means ontology classes. After determining the classification of the input document, we classify the appropriate sentence according to attributes belonging to the classification. Finally, we extract knowledge from sentences that are classified as appropriate, and we convert knowledge into a form of triples. In order to train models, we generated training data set from Wikipedia dump using a method to add BIO tags to sentences, so we trained about 200 classes and about 2,500 relations for extracting knowledge. Furthermore, we evaluated comparative experiments of CRF and Bi-LSTM-CRF for the knowledge extraction process. Through this proposed process, it is possible to utilize structured knowledge by extracting knowledge according to the ontology schema fro... 최근 4차 산업혁명과 함께 인공지능 기술에 대한 연구가 활발히 진행되고 있으며, 이전의 그 어느 때보다도기술의 발전이 빠르게 진행되고 있는 추세이다. 이러한 인공지능 환경에서 양질의 지식베이스는 인공지능 기술의 향상 및 사용자 경험을 높이기 위한 기반 기술로써 중요한 역할을 하고 있다. 특히 최근에는 인공지능 스피커를 통한 질의응답과 같은 서비스의 기반 지식으로 활용되고 있다. 하지만 지식베이스를 구축하는 것은 사람의 많은 노력을 요하며, 이로 인해 지식을 구축하는데 많은 시간과 비용이 소모된다. 이러한 문제를 해결하기위해 본 연구에서는 기계학습을 이용하여 지식베이스의 구조에 따라 학습을 수행하고, 이를 통해 자연어 문서로부터 지식을 추출하여 지식화하는 방법에 대해 제안하고자 한다. 이러한 방법의 적절성을 보이기 위해DBpedia 온톨로지의 구조를 기반으로 학습을 수행하여 지식을 구축할 것이다. 즉, DBpedia의 온톨로지 구조에따라 위키피디아 문서에 기술되어 있는 인포박스를 이용하여 학습을 수행하고 이를 바탕으로 자연어 텍스트로부터 지식을 추출하여 온톨로지화하기 위한 방법론을 제안하고자 한다. 학습을 바탕으로 지식을 추출하기 위한과정은 문서 분류, 적합 문장 분류, 그리고 지식 추출 및 지식베이스 변환의 과정으로 이루어진다. 이와 같은방법론에 따라 실제 지식 추출을 위한 플랫폼을 구축하였으며, 실험을 통해 본 연구에서 제안하고자 하는 방법론이 지식을 확장하는데 있어 유용하게 활용될 수 있음을 증명하였다. 이러한 방법을 통해 구축된 지식은 향후지식베이스를 기반으로 한 인공지능을 위해 활용될 수 있을 것으로 판단된다.

Knowledge- Evolutionary Intelligent Machine-Tools - Part 1 : Design of Dialogue Agent based on Standard Platform

Kim, Dong-Hoon,Song, Jun-Yeob The Korean Society of Mechanical Engineers 2006 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.20 No.11

In FMS (Flexible Manufacturing System) and CIM (Computer Integrated Manufacturing), machine-tools have been the target of integration in the last three decades. The conventional concept of integration is being changed into the autonomous manufacturing device based on the knowledge evolution by applying advanced information technology in which an open architecture controller, high-speed network and internet technology are included. In the advanced environment, the machine-tools is not the target of integration anymore, but has been the key subject of cooperation. In the near future, machine-tools will be more improved in the form of a knowledge-evolutionary intelligent device. The final goal of this study is to develop an intelligent machine having knowledge-evolution capability and a management system based on internet operability. The knowledge-evolutionary intelligent machine-tools is expected to gather knowledge autonomically, by producing knowledge, understanding knowledge, reasoning knowledge, making a new decision, dialoguing with other machines, etc. The concept of the knowledge-evolutionary intelligent machine is originated from the machine control being operated by human experts' sense, dialogue and decision. The structure of knowledge evolution in M2M (Machine to Machine) and the scheme for a dialogue agent among agent-based modules such as a sensory agent, a dialogue agent and an expert system (decision support agent) are presented in this paper, with intent to develop the knowledge-evolutionary machine-tools. The dialogue agent functions as an interface for inter-machine cooperation. To design the dialogue agent module in an M2M environment, FIPA (Foundation of Intelligent Physical Agent) standard platform and the ping agent based on FIPA are analyzed in this study. In addition, the dialogue agent is designed and applied to recommend cutting conditions and thermal error compensation in a tapping machine. The knowledge-evolutionary machine-tools are expected easily implemented on the basis of this study and shows a good assistance to sensory and decision support agents.

지리교육과정에서 내용으로서 지식에 대한 논의

서태열 ( Tae Yeol Seo ) 한국지리환경교육학회 2002 한국지리환경교육학회지 Vol.10 No.1

Recent changes in educational environments demands systematic perspectives on geography curriculum as a operative system with several interacting components. And more deep speculation into the nature and forms of knowledge as key content in geography education and geography curriculum is needed. Geographical knowledge in education can be divided into declarative geographical knowledge and procedural geographical knowledge which includes practice, procedure and performance in geography. As attentions must be paid to procedural knowledge to utilize academic wisdom and thinking ways in geography, as to personal and tacit knowledge to expand knowledge and to gain concrete knowledge. Considering the procedural knowledge and personal knowledge as important components in contents in geographical education, the possibility to achieve networking knowledge and problem solving ability will be getting high. Through this recognition, geographical education will be more educational, and geographical thinking and geographical inquiry will be interwoven meaningfully together.

지식사회 ‘현상’인가 ‘환상’인가?: 지식사회 담론의 이론적 쟁점과 전망

김종길(Kim, Jong-Kil) 동양사회사상학회 2018 사회사상과 문화 Vol.21 No.1

최근 지식의 중요성이 강조되고 지식의 생산·전파·공유 기술이 발달하 면서 현 시대에 내장된 지식사회 잠재력과 한계 및 그 미래 전망에 대한 논의도 활발해지고 있다. 1950년대 정보경제론, 1960년대 탈산업사회 론, 1980-90년대 정보사회론, 2000년대 지식사회론을 거치면서 확인된 정보 및 지식의 사회변동 잠재력은 오늘날 지식사회가 사회과학 담론의 핵심 아젠다 중 하나로 자리매김하는 데 일조했다. 본고는 지식사회 담론의 형성과 전개과정 및 쟁점들을 살펴보고 그것이 한국사회에 갖는 함의를 천착한다. 연구 결과에서 보듯 오늘의 사회에서는 광범위한 인구 집단이 지식 창출과 공유 및 확산에 참여하고 있고 개인생애의 전(全)주 기에 걸쳐 지식 습득의 중요성이 강조되고 있으며 지식이 주요 의사결 정과 행동의 타당성을 판별하는 준거가 된다는 점에서 지식사회로 볼수 있다. 하지만 우리가 마주하는 지식사회는 단순히 지식이 비약적으로 증가하고 확산된, 그래서 이에 대한 대중의 접근이 용이하게 된 사회가 아니다. 그것은 지식 증가에 비례해 무지, 불확실성, 위험, 공포도 증가 하는 역설적 사회이다. 인간이 삶의 질 향상을 목표로 과학기술 패러다 임을 밀어붙이면 붙일수록 인간의 삶을 위협하는 공포와 위험도 증가하는 패러독스, 그리고 과학지식 패러다임이 관철되면 될수록 인간의 인식 능력과 감각기관을 무력화하는 과학적 무지가 증가하는 패러독스는 우리가 몸담고 있는 현실 지식사회의 속절없는 자화상이다. Nowadays, as the importance of knowledge is emphasized and the technology for production, propagation, and sharing of knowledge has developed, discussions on the possibilities, limitations, and future prospects of the knowledge society are becoming more active as well.The potential of knowledge and information for social change, identified through discussions of the information economy of the 1950s, the post-industrial society of the 1960s, the information society of the 1980s and ’90s, and the knowledge society of the 2000s, has helped the knowledge society to become a key agenda of social science discourse. This article examines the formation and development of knowledge society dialogue, several related issues, and their implications for Korean society. As the research shows, today s society is a knowledge society in that, first, a broad range of people are involved in creating, sharing, and spreading knowledge; second, knowledge acquisition is an important part of everyone’s life cycle; and finally, knowledge becomes the basis for all decisions and actions. However, the knowledge society we face today is not simply one where accessibility is heightened by the increase and spread of knowledge. It is a paradoxical society in which fear, ignorance, risk, and uncertainty increase as knowledge increases. The reality of the knowledge society we face clearly portrays the paradox that human lives are more at risk as we push the frontiers of science and technology as well as the fact that ignorance increases as scientific paradigms spread throughout society.

Reflective Analysis on Knowledge-Building Community: Case of a Graduate Course

Hyunmi Chung 서울대학교 교육종합연구원 2001 The SNU Journal of Education Research Vol.10 No.-

This study focused on investigating design issues associated with establishing a classroom-based Knowledge-Building Community. Three design issues for establishing a KBC were investigated: (1) How to coordinate the efforts of individuals effectively in building collective knowledge, (2) How to support self-directed, knowledge-creation processes of individuals, (3) How to facilitate students` ownership of a Knowledge-Building Community. An instructional team designed a graduate course, Alternate Views of Teaching and Learning (Altviews), to foster a Classroom-Based Knowledge-Building Community toward studying alternative methods of teaching and learning. Instructional activities (interventions) for making effective distribution of individuals efforts, facilitating self-directed learning, and promoting the ownership of the KBC were embedded into the Altviews course. The course had three main phases: the Guided Reading Phase, the Sort and Sequence Phase, and the On-line Research Group Phase. The course was supported by Construe, a type of groupware, and Web Board conferencing software. The purpose of this article is to provide instructional designers with insights or guidelines for designing a Knowledge-Building Community in classroom settings by describing the graduate course designed with Knowledge-Building Community approach and reflecting on the course in terms of fostering a Knowledge-Building Community. In this article, the design featuresof the Altviews course, reflection on the Altivews course and emerging issues in building a Knowledge-Building Community were described. Also, implications for the design of Knowledge-Building Community were suggested.

호텔기업의 지식경영활동이 지식경영성과에 미치는 영향

신동주,선우영수 한국관광연구학회 2009 관광연구저널 Vol.23 No.3

In today’s knowledge-based society, knowledge makes major contributions to the generation of individual’s value added through creation, spread, distribution, and utilization and serves as one of the principal sources of national competitivity. But hotel corporations whose dependence on their organizational members have neglected the importance of knowledge management activities. The ultimate goal of hotel corporations is to maintain their existence by securing competitive advantages over their competitors. In order to secure competitive advantages, they need to shed off the conventional paradigm of company management, which increasingly grows weaker as the industrial society turns into a knowledge-based one, and make effective use of knowledge, which is the core source of their wealth and competitivity, in their management. Thus this study set out to identify factors of knowledge management activity to result in great management performance to hotel corporations. It also aimed to suggest specific action plans for them to do knowledge management efficiently based on the results.

Knowledge Extractions, Visualizations, and Inference from the big Data in Healthcare and Medical

Kim, Jin Sung Korean Institute of Intelligent Systems 2013 한국지능시스템학회논문지 Vol.23 No.5

The purpose of this study is to develop a composite platform for knowledge extractions, visualizations, and inference. Generally, the big data sets were frequently used in the healthcare and medical area. To help the knowledge managers/users working in the field, this study is focused on knowledge management (KM) based on Data Mining (DM), Knowledge Distribution Map (KDM), Decision Tree (DT), RDBMS, and SQL-inference. The proposed mechanism is composed of five key processes. Firstly, in Knowledge Parsing, it extracts logical rules from a big data set by using DM technology. Then it transforms the rules into RDB tables. Secondly, through Knowledge Maintenance, it refines and manages the knowledge to be ready for the computing of knowledge distributions. Thirdly, in Knowledge Distribution process, we can see the knowledge distributions by using the DT mechanism.Fourthly, in Knowledge Hierarchy, the platform shows the hierarchy of the knowledge. Finally, in Inference, it deduce the conclusions by using the given facts and data.This approach presents the advantages of diversity in knowledge representations and inference to improve the quality of computer-based medical diagnosis.

New propositions for Strategic Knowledge Curation

한병석,배경훈,강형구 아시아.유럽미래학회 2019 유라시아연구 Vol.16 No.2

How to acquire and to produce important information is critical. How to manage knowledge is also a significant topic in social science. Recently, as the amount of information has exploded, it becomes more important how to organize existing information and to turn much information into valuable knowledge. Furthermore, it is crucial for people to select the right information for themselves. In other words, in the vast ocean of information, we must be able to gather and classify useful information. Knowledge curation, as a management process of reorganization of information, is a promising strategy. Knowledge curation is an interesting concept. Curation originally meant the selection and care of objects to be shown in a museum, but now is used as a reorganization of the information. Knowledge curation services have grown due to both demand and supply factors. From the demand side, as there are too many choice alternatives about contents, the demand for contents curation increases. Contrary to common sense, too many choice alternatives can reduce the utility of consumers. From the supply side, as the cost of contents decreases, curation becomes cheaper. In addition, big data technologies make it possible to offer customized knowledge curation to consumers. However, existing knowledge management literature has not clearly incorporated this new concept yet. In this paper, we suggest a novel framework for knowledge curation in line with existing knowledge management literature. To our knowledge, this is the first paper to catalog knowledge curation on its goals and processes. This paper will make this emergent concept more useful and in turn, contribute to the body of knowledge management literature. We classify knowledge curation based on its process and its orientation. This classification yields four approaches to knowledge curation: news approach, museum approach, networking approach and open innovation approach. Four types of knowledge curation are summarized as below. When knowledge curation is to communicate existing knowledge in unilateral direction, it becomes the news approach. When it is to communicate existing knowledge through multilateral flow, it becomes the networking approach. When the goal of knowledge curation is creating new knowledge through unilateral information flow, the museum approach emerges. Lastly, when knowledge curation aims to create new knowledge through multilateral interactions between participants, it is the open innovation approach. And we suggest required roles for knowledge curator according to each approach. The news approach requires curators to become lecturer, the museum approach does researcher, the network approach does moderator, and the open innovation approach does innovation manager. Also, we suggest how to implement knowledge curation successfully. The suggested process describes the generic process that can be applied to all models of knowledge curation. It is desirable to repeat this procedure until the marginal cost of the procedure iteration is greater than the marginal utility. Future research can enrich this research with further qualitative and quantitative analysis.

개인적·사회적 요인을 고려한 가상 공동체에서의 지식 공유 모형

최경선 ( Choi Kyungsun ),안현철 ( Ahn Hyunchul ) 한국정보시스템학회 2019 정보시스템연구 Vol.28 No.1

Purpose Virtual communities (VCs) are becoming ever more important in these days, sometimes more than offline communities. Notably, they have become significant sources of knowledge sharing. Therefore, in order to foster a VC, it is very important to understand why people share their knowledge in the VC. Under this background, this paper aims at proposing the behavioral model best explains knowledge sharing activities in VCs. Design/methodology/approach We basically design our behavioral model for knowledge sharing in VCs based on theory of reasoned action (TRA). However, to understand knowledge sharing in VCs better, we specify knowledge sharing by dividing it into knowledge contribution and knowledge use. Also, instead of ‘subjective norm’, we adopt ‘sense of virtual community (SOVC)’ as a main social factor, which has been found to be important in the literature. We also include the antecedents such as ‘quality of the shared knowledge’, ‘trust in community members’, ‘passion of the community leader’, ‘reciprocity’, and ‘self efficacy’, which affect VC users’attitude towards knowledge sharing and SOVC. To test the hypotheses in our proposed model, we collected 253 valid surveys from the VC users. Structural equation modeling (SEM) using AMOS 23 is employed to assess the relationships proposed as the hypotheses. Findings Major findings are as follows. SOVC positively affects both intention to contribute knowledge and intention to use knowledge. And, trust in community members positively affects the attitude towards knowledge use and SOVC. The attitude towards knowledge use is also affected by the quality of the shared knowledge. Reciprocity is found to strongly positively affect the attitude towards knowledge contribution. However, passion of the community leader and self efficacy are found to have insignificant effect on SOVC and the attitude towards knowledge contribution respectively. Our study sheds a light on how to foster VCs from the perspective of knowledge management.

Knowledge-Evolutionary Intelligent Machine-Tools

Dong-Hoon Kim,Jun-Yeob Song 대한기계학회 2006 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.20 No.11

In FMS (Flexible Manufacturing System) and CIM (Computer Integrated Manufacturing), machine-tools have been the target of integration in the last three decades. The conventional concept of integration is being changed into the autonomous manufacturing device based on the knowledge evolution by applying advanced information technology in which an open architecture controller, high-speed network and internet technology are included. In the advanced environment, the machine-tools is not the target of integration anymore, but has been the key subject of cooperation. In the near future, machine-tools will be more improved in the form of a knowledge-evolutionary intelligent device. The final goal of this study is to develop an intelligent machine having knowledge-evolution capability and a management system based on internet operability. The knowledge-evolutionary intelligent machine-tools is expected to gather knowledge autonomically, by producing knowledge, understanding knowledge, reasoning knowledge, making a new decision, dialoguing with other machines, etc. The concept of the knowledge-evolutionary intelligent machine is originated from the machine control being operated by human experts’ sense, dialogue and decision. The structure of knowledge evolution in M2M (Machine to Machine) and the scheme for a dialogue agent among agent-based modules such as a sensory agent, a dialogue agent and an expert system (decision support agent) are presented in this paper, with intent to develop the knowledge-evolutionary machine-tools. The dialogue agent functions as an interface for inter-machine cooperation. To design the dialogue agent module in an M2M environment, FIPA (Foundation of Intelligent Physical Agent) standard platform and the ping agent based on FIPA are analyzed in this study. In addition, the dialogue agent is designed and applied to recommend cutting conditions and thermal error compensation in a tapping machine. The knowledge-evolutionary machine-tools are expected easily implemented on the basis of this study and shows a good assistance to sensory and decision support agents.