• 한국경영정보학회:학술대회논문집
• /
• 2008.06a
• /
• pp.288-293
• /
• 2008

의미적 지식기반인 온톨로지(ontology)에 대한 관심이 높아지고 있다. 온톨로지란 어휘나 개념의 정의 또는 명세로서, 인간과 컴퓨터의 의사소통 또는 지식의 표현과 저장, 활용 및 재사용을 위해 이용된다. 그러나 온톨로지를 구축하는 대부분의 방법은 체계적이거나 자동적이지 못하다. 도메인 전문가에 의존하는 전통적인 온톨로지 구축 방법은 시간과 비용이 많이 소요된다. 온톨로지 구축 툴은 많이 있지만 아직 인간의 노력을 필요로 한다. 또한 변화하는 도메인 지식을 온톨로지에 신속하게 반영하는 것은 어려운 일이다. 본 연구는 이러한 한계를 해결하기 위해, 도메인 전문가의 지식이나 경험을 최소화하면서 자동적으로 도메인 지식을 얻을 수 있는 방법을 제시하였다. 이 방법은, 데이터 기반의 도메인 지식을 대상으로, 베이지안 망(Bayesian network)이 갖고 있는 데이터 분석에서의 장점과 온톨로지와의 관련성을 이용하여 온톨로지를 자동적으로 구축하는 것이다. 평판(flat panel) TV 경기예측 사례를 통하여 온톨로지를 구축하는 과정을 알아보았다. 구축과정의 타당성을 확보하기 위하여 디스플레이 산업 전문가들과의 인터뷰를 통하여 온톨로지를 완성하고, 해당 온톨로지의 타당성 검증을 위하여 멤버체크를 한 결과 매우 높은 타당성을 얻을 수 있었다. 본 연구에서 제안하는 온톨로지는, 실제로 산업경기 예측을 계획하고 구축하며 미래 의사결정지원시스템을 설계하기 위한 주요 구성요인으로 제공될 수 있을 것이다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.3
• /
• pp.79-87
• /
• 2024

Recently, the importance of pre-trained language models (PLM) has been emphasized for natural language processing (NLP) such as text classification, sentiment analysis, and question answering. Korean PLM shows high performance in NLP in general-purpose domains, but is weak in domains such as finance, medicine, and law. The main goal of this study is to propose a language model learning process and method to build a financial-specific language model that shows good performance not only in the financial domain but also in general-purpose domains. The five steps of the financial-specific language model are (1) financial data collection and preprocessing, (2) selection of model architecture such as PLM or foundation model, (3) domain data learning and instruction tuning, (4) model verification and evaluation, and (5) model deployment and utilization. Through this, a method for constructing pre-learning data that takes advantage of the characteristics of the financial domain and an efficient LLM training method, adaptive learning and instruction tuning techniques, were presented.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.05a
• /
• pp.687-689
• /
• 2007

본 논문은 2005 년부터 2006 년도까지 정보통신부의 지원 하에 한국전자통신연구원 언어처리연구팀에서 성공적으로 개발하여 현재 산업자원부 특허지원센터에서 대용량의 영어 특허문서를 대상으로 한국어 자동번역 서비스를 제공하고 있는 특허 전문 영한 번역기에 대해 기술한다. 특히 본 논문에서는 일반 도메인을 대상으로 한 기존의 영한 번역기를 제한된 도메인을 대상으로 한 영한번역기로 개량하고자 할 때, 개량하는 방법으로써 제한된 도메인에 대한 특화 절차에 대해서 기술한다. 이와 같이 특화 절차에 따라 구축된 특허 전문 영한 번역기 번역률을 특허 분야 중에 주요 5개 분야(기계, 전기전자, 화학일반, 의료위생, 컴퓨터)에 대해 특허전문번역가가 평가한 결과, 평균 82.43%가 나왔다. 또한 전기전자 분야 특허문서를 대상으로 특허 전문 영한 번역기와 일반 도메인을 대상으로 한 영한 번역기와의 번역률을 평가한 결과, 특허 전문 영한 번역기는 82.20%, 일반 도메인 대상 영한 번역기는 54.25%의 번역률을 내어, 특허에 특화된 특허 전문 영한 번역기가 특화되지 않은 일반 도메인의 영한 번역기에 비해 27.95%나 더 높은 결과를 알 수 있었다.

• Journal of the Korea Computer Industry Society
• /
• v.5 no.8
• /
• pp.811-818
• /
• 2004

The spreading of internet, combined with the computerization of industry and the life whole has created an incereased demand on the private life protection and information portection, but due to the lack of specialty manpower on the information protection industry field there are many difficulties. Therefore, in this paper a curriculum for an information protection specialty manpower training is proposed. The proposed curriculum indispensability 1,2 and classified with a selection 1,2 and classified with a selection 1,2. The information protection application field into 9 segments of domains, and to carry out the curriculum in a ring structure. The curriculum based on the information security field's 9 domains and related field practical business, and the course offered after graduation to deepen the specialty, need to be carried out by each domain in order to continuously carry out the information security deepening process.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.95-99
• /
• 2022

오픈 도메인 질의 응답 (ODQA, Open-Domain Question Answering)은 주어진 질문에 대한 답을 찾는 과업으로서 질문과 관련있는 지식을 찾는 "검색" 단계를 필요로 한다. 최근 이미지, 테이블 등의 검색을 요구하는 멀티 모달 ODQA에 대한 연구가 많이 진행되었을 뿐만 아니라 산업에서의 중요도 또한 높아지고 있다. 본 논문은 여러 종류의 멀티 모달 ODQA 중에서도 테이블 - 텍스트 기반 멀티 모달 ODQA 데이터 집합으로 Fusion-in-Decoder (FiD)를 이용한 멀티 모달 오픈 도메인 질의 응답 연구를 제안하며 베이스라인 대비 최대 EM 20.5, F1 23.2 향상을 보였다.

• The Journal of Bigdata
• /
• v.3 no.2
• /
• pp.11-18
• /
• 2018

This study is a study on domain automatic classification for domain - based quality diagnosis which is a key element of big data quality diagnosis. With the increase of the value and utilization of Big Data and the rise of the Fourth Industrial Revolution, the world is making efforts to create new value by utilizing big data in various fields converged with IT such as law, medical, and finance. However, analysis based on low-reliability data results in critical problems in both the process and the result, and it is also difficult to believe that judgments based on the analysis results. Although the need of highly reliable data has also increased, research on the quality of data and its results have been insufficient. The purpose of this study is to shorten the work time to automizing the domain classification work which was performed from manually to using machine learning in the domain - based quality diagnosis, which is a key element of diagnostic evaluation for improving data quality. Extracts information about the characteristics of the data that is stored in the database and identifies the domain, and then featurize it, and automizes the domain classification using machine learning. We will use it for big data quality diagnosis and contribute to quality improvement.

• Journal of Industrial Convergence
• /
• v.21 no.12
• /
• pp.37-43
• /
• 2023

In today's business landscape, collaboration and interoperability are crucial for organizational success and profitability. However, integrating operations across multiple organizations is challenging due to differing roles and policies in Identity and Access Management (IAM). User-centric identity (UCI) adopts a personalized approach to digital identity management, centering on the end-user for authentication and access control. It provides a decentralized system that ensures secure and customized access for each user. UCI aims to address complex security challenges by aligning access privileges with individual user requirements. This research delves into UCI's ability to streamline resource access amidst conflicting IAM roles and protocols across various organizations. The study presents a UCI-based multi-domain access control (MDAC) framework, which encompasses an ontology, a unified method for articulating access roles and policies across domains, and software services melding with UCI infrastructure. The goal is to enhance organizational resource management and decision-making by offering clear guidelines on access roles and policy management across diverse domains, ultimately boosting companies' return on investment.

• Database Research
• /
• v.34 no.3
• /
• pp.137-147
• /
• 2018

A key to a well-performing human activity recognition (HAR) system through machine learning technique is the availability of a substantial amount of labeled data. Collecting sufficient labeled data is an expensive and time-consuming task. To build a HAR system in a new environment (i.e., the target domain) with very limited labeled data, it is unfavorable to naively exploit the data or trained classifier model from the existing environment (i.e., the source domain) as it is due to the domain difference. While traditional machine learning approaches are unable to address such distribution mismatch, transfer learning approach leverages the utilization of knowledge from existing well-established source domains that help to build an accurate classifier in the target domain. In this work, we propose a transfer learning approach to create an accurate HAR classifier with very limited data through the multitask neural network. The classifier loss function minimization for source and target domain are treated as two different tasks. The knowledge transfer is performed by simultaneously minimizing the loss function of both tasks using a single neural network model. Furthermore, we utilize the unlabeled data in an unsupervised manner to help the model training. The experiment result shows that the proposed work consistently outperforms existing approaches.

• The Journal of Bigdata
• /
• v.7 no.1
• /
• pp.89-97
• /
• 2022

Various efforts are needed to prevent accidents because ship collisions can cause various negative situations such as economic losses and casualties. Therefore, research to prevent accidents is being actively conducted, and in this study, new leading indicators for preventing ship collision accidents is proposed. In previous studies, the risk of collision was expressed in consideration of the distance between ships in a specific sea area, but there is a disadvantage that a new model needs to be developed to apply this to other sea areas. In this study, the density-based ship domain DESD (Density-based Empirical Ship Domain) including the environment and operating characteristics of the sea area was defined using AIS (Automatic Identification System) data, which is ship operation information. Deep clustering is applied to two-dimensional DESDs created for each sea area to cluster the seas with similar operating environments. Through the analysis of the relationship between clustered sea areas and ship collision accidents, it was statistically tested that the occurrence of accidents varies by characteristic of each sea area, and it was proved that DESD can be used as a leading indicator of accidents.

• Journal of the Korea Computer Industry Society
• /
• v.3 no.8
• /
• pp.1049-1062
• /
• 2002

As the distributed resources in the networks have become increasingly popular, the accesses to these resources having been activated. Especially, the accesses to the distributed resources using the mobile agent technologies provide the mechanisms supporting mobility with mobile users as well as the dynamic accesses to the resources in the fixed networks. Proxy-based mobile agent model is defined as mobile agent network model which allocates the hierarchical domains to the distributed resources changed dynamically, assigns one proxy server for each domain, and promotes the management and the cooperation of the mobile agents. In this paper, we introduce the architecture and the execution scenario for proxy-based mobile agent model which is suitable for the hierarchical management domains. In simulation, we evaluate the proxy server's route optimization functionality and the performance reducing execution time of the mobile agents.