• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.219-224
• /
• 2022

최근 딥러닝이 상식 정보를 추론하지 못하거나, 해석 불가능하다는 한계점을 보완하기 위해 지식 그래프를 기반으로 자연어 텍스트를 생성하는 연구가 중요하게 수행되고 있다. 그러나 이를 위해서 대량의 지식 그래프와 이에 대응되는 문장쌍이 요구되는데, 이를 구축하는 데는 시간과 비용이 많이 소요되는 한계점이 존재한다. 또한 하나의 그래프에 다수의 문장을 생성할 수 있기에 구축자 별로 품질 차이가 발생하게 되고, 데이터 균등성에 문제가 발생하게 된다. 이에 본 논문은 공개된 지식 그래프인 디비피디아를 활용하여 전문가의 도움 없이 자동으로 데이터를 쉽고 빠르게 구축하는 방법론을 제안한다. 이를 기반으로 KoBART와 mBART, mT5와 같은 한국어를 포함한 대용량 언어모델을 활용하여 문장 생성 실험을 진행하였다. 실험 결과 mBART를 활용하여 미세 조정 학습을 진행한 모델이 좋은 성능을 보였고, 자연스러운 문장을 생성하는데 효과적임을 확인하였다.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.185-189
• /
• 2019

관계추출기의 학습을 위해서는 많은 학습 데이터가 필요한데, 사람이 모으게 되면 많은 비용이 필요하여 원격 지도 학습을 이용한 데이터 수집이 많은 연구에서 사용되고 있다. 원격 지도 학습은 지식베이스를 기반으로 학습 데이터를 자동으로 만들어 내는 방식이기에 비용이 거의 들지 않지만, 지식베이스의 질과 양에 영향을 받는다. 본 연구는 원격 지도 학습을 기본으로 관계추출기의 성능을 향상 시키고, 지식베이스를 확장하는 방안으로 반복학습을 제안한다. 실험을 적은 비용으로 빠르게 진행하기 위해 반복학습을 자동화 하는 시스템을 설계하여 실험을 하였고, 이 시스템으로 관계추출기의 성능이 향상 될 수 있는 가능성을 보였으며, 반복학습을 통한 지식베이스의 확장 방안을 제시한다.

• The KIPS Transactions:PartB
• /
• v.15B no.2
• /
• pp.147-158
• /
• 2008

Fuzzy Cognitive Map (FCM) and Bayesian Belief Network (BBN) are two major frameworks for modeling, representing and reasoning about causal knowledge. Despite their extensive use in causal knowledge engineering, there is no reported work which compares their respective roles. This paper aims to fill the gap by providing a qualitative comparison of the two frameworks through a systematic analysis based on some inherent features of the frameworks. We proposed a set of comparison criteria which covers the entire process of causal knowledge engineering, including modeling, representation, and reasoning. These criteria are usability, expressiveness, reasoning capability, formality, and soundness. The results of comparison have revealed some important facts about the characteristics of FCM and BBN, which will help to determine how FCM and BBN should be used, with respect to each other, in causal knowledge engineering.

• The Journal of Korean Institute for Practical Engineering Education
• /
• v.2 no.2
• /
• pp.68-73
• /
• 2010

For engineers in the knowledge-based society of the 21st century, not only the specialty in their major field, but also the capabilities of creative thinking/reading/writing, of communication and of understanding society/business/economy, and the knowledge of specialized liberal arts, like ethics, are required. For the specialized liberal arts knowledge, it is important to have interest in a field, read the relevant literature, and summarize and express thoughts, but in reality, it is difficult to accomplish a higher level of learning outcome within the limited regular curriculum. In this study, an application for smart phones that purports to cultivate the specialized liberal arts knowledge of the students enrolled in the college of engineering was developed and applied to classes. Under this environment, a teacher can interact with teacher's students through the structured knowledge on a real-time basis in any place at any time, and the students can reorganize the knowledge by themselves. In this way, this paper proposed a way of improving the level of specialized liberal arts knowledge in daily life.

• Progress in Superconductivity and Cryogenics
• /
• v.12 no.3
• /
• pp.21-24
• /
• 2010

A cryogenic insulation technique for a high voltage and a large current capacity of a conductor are now two big issues in a field of recent R&D projects of superconducting power devices, especially a superconducting power transformer. For the large rated currents of the power transformer, it is well known that lots of 2nd generation superconducting conductor, so called coated conductor, should be stacked together with transpositions in order to get an even distributions of the currents. We had come up with an idea of a CTCC (Continuously Transposed Coated Conductor) as a conductor for a large power superconducting transformer, and keep trying to verify the usefulness of the conductor. As one of the efforts of verifying, we prepared and tested a sample CTCC with insulations for high voltage, which includes the epoxy coating and Nomex$^{(R)}$ wrapping. This paper contains the insulation process and dielectric breakdown test results. We expect the results obtained from this experiment to improve an insulation technique for high voltages in various cryogenic environments[1,2].

• Superconductivity and Cryogenics
• /
• v.3 no.1
• /
• pp.2-5
• /
• 2001

• The Magazine of the IEIE
• /
• v.15 no.3
• /
• pp.57-64
• /
• 1988

• Proceedings of the Zoological Society Korea Conference
• /
• 1995.10b
• /
• pp.361.2-361
• /
• 1995

• The Journal of Information Systems
• /
• v.29 no.4
• /
• pp.123-135
• /
• 2020

Purpose The purpose of this study is to investigate the development process and the effectiveness of the EISS (epidemiological investigation support system), which prevents the spread of infectious diseases like a novel corona virus disease, COVID-19. Design/methodology/approach This study identified the existing epidemiological support system for MERS through prior research and studied the case of the development of a newly developed epidemiological support system based on cloud computing infrastructure for COVID-19 through inter-ministerial collaboration in 2020. Findings The outbreak of COVID-19 drove the Korean Government began the development of the EISS with private companies. This system played a significant role in flattening the spread of infection during several waves in which the number of confirmed cases increased rapidly in Korea, However, we need to be careful in handling confirmed patients' private data affecting their privacy.

• Annual Conference on Human and Language Technology
• /
• 1995.10a
• /
• pp.253-257
• /
• 1995

본 논문은 DCS(Dynamic Comprehension System) 정보확장 과정을 어휘 정보의 첨가를 통해 묘사하고자한다. 즉, 현존의 사전정보의 보완작용없이, 시스템을 확장하는 과정이 이 논문에서 보여진다. 새로운 언어정보에 유연하게 대처하기 위해 화자와 청자간의 새로운 지식의 학습과정이 나무구조 형식의 보조메뉴를 통해 상호 교환방식으로 나타내진다. 본 논문은 새로운 지식의 인지과정 중 현존의 정보망(network)에 각 단위망(nection)이 첨가될 때의 과정을 구현시키고자 시도된 것이다.