• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.11 no.4
• /
• pp.119-123
• /
• 2011

In recent years, several technologies have brought many changes in the field of education. Nonetheless, it is difficult to get freely medical and professional knowledge in the educational environment. In this paper, we study a free medical education system for medical education through service to the Mashup offers a meta-search system. Received permission to use the system API to retrieve the content API, data retrieval systems and video content via the API to design a system, based on this medical education, meta-search system is implemented.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.1
• /
• pp.88-93
• /
• 2001

기존의 데이터베이스 검색시스템은 사용자의 검색 조건에 정확히 일치하는 데이터가 데이터베이스 내에 존재할 경우에만 사용자에게 해당 데이터를 제공할 수 있고, 사용자의 검색조건을 정확히 만족하는 데이터가 없을 경우에는 적절한 데이터를 제공할 수 없는 문제점이 있다. 이러한 문제를 해결하기 위하여 본 논문에서는 FCM의 클러스터증가 및 재초기화 알고리즘을 제안하였고, FCM을 이용하여 데이터베이스 내의 데이터로부터 구축된 지식기반 데이터베이스(KDB)와 구축된 이미지 데이터베이스와 연동을 통하여 사용자의 요구에 가장 근접한 데이터를 제시해 주는 검색시스템을 제안하였다. 본 연구에서 제안된 수법을 우체국의 우편주문안내책자를 이용한 선물고르기 DB 검색 시스템에 적용하여 그 유효성을 확인하였다.

• Journal of KIISE:Computing Practices and Letters
• /
• v.5 no.1
• /
• pp.14-28
• /
• 1999

최근 멀티미디어 데이터로부터 내용에 대한 정보를 추출하여 데이터베이스에 저장하고 내용에 기반한 질의를 수행하도록 하는 내용 기반 검색 시스템이 중요한 핵심 기술로 대두되고 있다. 본 논문에서는 내용 기반 멀티미디어 검색 시스템인 COSMIC(Content Based Multimedia Information Processor)의 설계 및 구현에 관하여 기술한다. COSMIC은 대용량 이미지 데이터로부터 자동으로 추출된 시각적 특징 데이터들을 다차원 점접근 방법(Point Access Method)인 HG-트리를 이용하여 색인하고 예제 이미지와 사용자가 그린 스케치에 의한 시각적 질의를 제공한다. 또한 COSMIC은 비디오 데이터로부터 추출된 다양한 의미 정보를 이용하여 의미 질의를 제공한다. COSMIC의 유효성을 입증하기 위해서 다양한 시각적 질의와 이미 질의를 이용한 실험을 수행하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10b
• /
• pp.102-104
• /
• 2000

현재 인터넷상의 정보와 문서의 양은 상상을 초월하는 증가추이를 나타내고 있다. 이와 더불어 표현하려는 목적에 따라 체계적으로 정리되고 정형화된 문서들 또한 증가하고 있다. 이러한 문서들 중에는 각 인터넷 신문사나 웹진과 같은 문서들이 포함되는데, 이러한 문서들은 각각의 내용구성과 표현 형식에 있어서 비슷한 구성을 지니고 있다. 본 논문에서는 이러한 체계적이고 정형화된 웹 뉴스 문서검색을 위하여 '지식기반 방식을 이용한 웹 뉴스문서 검색 에이전트 시스템'을 제안한다. 사용자는 시스템에서 제공하는 지식을 기반으로 검색하고자 하는 대상을 에이전트 시스템에게 요청하게 되고 지식기반을 이용한 에이전트 시스템은 보다 정확한 정보를 사용자에게 제공하게 된다.

• ETRI Journal
• /
• v.46 no.1
• /
• pp.11-21
• /
• 2024

We focus on open-domain question-answering tasks that involve a chain-of-reasoning, which are primarily implemented using large language models. With an emphasis on cost-effectiveness, we designed EffiChainQA, an architecture centered on the use of small language models. We employed a retrieval-based language model to address the limitations of large language models, such as the hallucination issue and the lack of updated knowledge. To enhance reasoning capabilities, we introduced a question decomposer that leverages a generative language model and serves as a key component in the chain-of-reasoning process. To generate training data for our question decomposer, we leveraged ChatGPT, which is known for its data augmentation ability. Comprehensive experiments were conducted using the HotpotQA dataset. Our method outperformed several established approaches, including the Chain-of-Thoughts approach, which is based on large language models. Moreover, our results are on par with those of state-of-the-art Retrieve-then-Read methods that utilize large language models.

• Journal of the Korean Society for Library and Information Science
• /
• v.40 no.1
• /
• pp.195-215
• /
• 2006

With the developments in the areas of IT and internet, the portal sites have provided a variety of services. The explosive growth of portal sites based on IR services has a great influence on information services and types of information provided typically by libraries. Because of various and useful information services, information users consider portal sites as a more useful information resource. With the user's changes in information resource the portal sites can be a threatening competitor to libraries as a information resource. To deal successfully environmental changes around libraries. IR agency service can be best solution. IR agency service is a sort of more advanced and expanded information services for information users who can not connect to internet or has no skill on IT area. In this paper, information users' opinion on their internet using behavior and IR agency service was collected and analyzed. Based on the result of survey. this paper proposes how to provide IR agency service and its expecting effect for libraries, especially public libraries.

• Journal of the Korean Society for information Management
• /
• v.23 no.2
• /
• pp.229-243
• /
• 2006

This study aims to suggest an effective way to enhance question-answer(QA) document retrieval performance by reconstructing queries based on the structural features in the QA documents. QA documents are a structured document which consists of three components : question from a questioner, short description on the question, answers chosen by the questioner. The study proposes the methods to reconstruct a new query using by two major structural parts, question and answer, and examines which component of a QA document could contribute to improve query performance. The major finding in this study is that to use answer document set is the most effective for reconstructing a new query. That is, queries reconstructed based on terms appeared on the answer document set provide the most relevant search results with reducing redundancy of retrieved documents.

• Journal of Korean Library and Information Science Society
• /
• v.47 no.1
• /
• pp.361-382
• /
• 2016

NTIS(National Science & Technology Information Service) is the first national R&D information knowledge portal service in the world to provide information of government-funded R&D projects and it has been developed by KISTI. This study investigated several limitations of current NTIS information service, analyzed information needs for end users, and then proposed information recomposition and visualization method to satisfy their information needs. For doing this, we firstly clarified the definition of 'end-users' and classified three different groups of general users. We also discriminated various information needs according to three groups and illustrated some examples of visualization results to meet the requirements - 'retrieval simplification' and 'information visualization'. To consider practicality of our proposed method, we suggested implementation plans to utilize existed NTIS services.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.1
• /
• pp.10-19
• /
• 2003

Caption information in news videos can be useful for video indexing and retrieval since it usually suggests or implies the contents of the video very well. In this paper, a new algorithm for extracting and recognizing characters from news video is proposed, without a priori knowledge such as font type, color, size of character. In the process of text region extraction, in order to improve the recognition rate for videos with complex background at low resolution, continuous frames with identical text regions are automatically detected to compose an average frame. The image of the averaged frame is projected to horizontal and vertical direction, and we apply region filling to remove backgrounds to produce the character. Then, K-means color clustering is applied to remove remaining backgrounds to produce the final text image. In the process of character recognition, simple features such as white run and zero-one transition from the center, are extracted from unknown characters. These feature are compared with the pre-composed character feature set to recognize the characters. Experimental results tested on various news videos show that the proposed method is superior in terms of caption extraction ability and character recognition rate.

• Korean Journal of Cognitive Science
• /
• v.14 no.1
• /
• pp.29-40
• /
• 2003

Cross-Language Information Retrieval (CLIR) deals with the documents in various languages by one language query. A user who uses one language can retrieve the documents in another language through CLIR system. In CLIR, query translation method is known to be more efficient. For the better performance of query translation, we need more resources like dictionary, ontology, and parallel/comparable corpus but usually not available. This paper proposes a new concept called the Common Base Axis which is adapted to Korean-English Query translation ann a new weighting method in dictionary based query translation. The essential idea is that we can express Korean and English word in one vector space by Common Base Axis and use it in calculating sense distance for query weighting. The experiments show that Common Base Axis gives us good performance without ontology and is especially good for one word query translation.