• Journal of the Korea Convergence Society
• /
• v.7 no.2
• /
• pp.19-24
• /
• 2016

On a huge space of information called the Internet, users can use a smart mobile web to get information on various intellectual fields and can access to various Medias such as personal blogs and social networking sites (SNS). This is why a vast amount of information on the web has been effectively managed and researched nowadays through a technology named Semantic Web. However, it still needs for an improvement for studies on searching for intellectual information, though it is enhanced to integrate variously spread information and search for intellectual information user-oriented. Thus, this study aims to research on searching information and knowledge spread around a knowledge-filled information space, which can improve credibility according to user-oriented logic.

• Genomics & Informatics
• /
• v.7 no.1
• /
• pp.38-40
• /
• 2009

The EST Knowledge Integrated System, EKIS (http://ekis.kribb.re.kr), was established as a part of Korea's Ministry of Education, Science and Technology initiative for genome sequencing and application research of the biological model organisms (GEAR) project. The goals of the EKIS are to collect EST information from GEAR projects and make an integrated database to provide transcriptomic and metabolomic information for biological scientists. The EKIS constitutes five independent categories and several retrieval systems in each category for incorporating massive EST data from high-throughput sequencing of 65 different species. Through the EKIS database, scientists can freely access information including BLAST functional annotation as well as Genechip and pathway information for KEGG. By integrating complex data into a framework of existing EST knowledge information, the EKIS provides new insights into specialized metabolic pathway information for an applied industrial material.

• International Journal of Computer Science & Network Security
• /
• v.22 no.6
• /
• pp.346-356
• /
• 2022

The jurisprudential legal rules govern the way Muslims react and interact to daily life. This creates a huge stream of questions, that require highly qualified and well-educated individuals, called Muftis. With Muslims representing almost 25% of the planet population, and the scarcity of qualified Muftis, this creates a demand supply problem calling for Automation solutions. This motivates the application of Artificial Intelligence (AI) to solve this problem, which requires a well-designed Question-Answering (QA) system to solve it. In this work, we propose a QA system, based on retrieval augmented generative transformer model for jurisprudential legal question. The main idea in the proposed architecture is the leverage of both state-of-the art transformer models, and the existing knowledge base of legal sources and question-answers. With the sensitivity of the domain in mind, due to its importance in Muslims daily lives, our design balances between exploitation of knowledge bases, and exploration provided by the generative transformer models. We collect a custom data set of 850,000 entries, that includes the question, answer, and category of the question. Our evaluation methodology is based on both quantitative and qualitative methods. We use metrics like BERTScore and METEOR to evaluate the precision and recall of the system. We also provide many qualitative results that show the quality of the generated answers, and how relevant they are to the asked questions.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.1
• /
• pp.35-40
• /
• 2022

In this paper, we propose a method of constructing clinical knowledge with clinical concept relations and predicting diseases based on a deep learning model to support clinical decision-making. Clinical terms in UMLS(Unified Medical Language System) and cancer-related medical knowledge are classified into five categories. Medical related documents in Wikipedia are extracted using the classified clinical terms. Clinical concept relations are established by matching the extracted medical related documents with the extracted clinical terms. After deep learning using clinical knowledge, a disease is predicted based on medical terms expressed in a query. Thereafter, medical terms related to the predicted disease are selected as an extended query for clinical document retrieval. To validate our method, we have experimented on TREC Clinical Decision Support (CDS) and TREC Precision Medicine (PM) test collections.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.125-130
• /
• 2022

최근 자연어처리 연구로 지식 기반 대화에서 대화 내용에 자유로운 주제와 다양한 지식을 포함하는 연구가 활발히 이루어지고 있다. 지식 기반 대화는 대화 내용이 주어질 때 특정 지식 정보를 포함하여 이어질 응답을 생성한다. 이때 대화에 필요한 지식이 검색 가능하여 선택에 제약이 없는 오픈 도메인(Open-domain) 지식 기반 대화가 가능하도록 한다. 오픈 도메인 지식 기반 대화의 성능 향상을 위해서는 대화에 이어지는 자연스러운 답변을 연속적으로 생성하는 응답 생성 모델의 성능 뿐만 아니라, 내용에 어울리는 응답이 생성될 수 있도록 적합한 지식을 선택하는 지식 검색 모델의 성능 향상도 매우 중요하다. 본 논문에서는 오픈 도메인 지식 기반 한국어 대화에서 지식 검색 성능을 높이기 위해 밀집 벡터 기반 검색 방식과 주제어(Keyword) 기반의 검색 방식을 함께 사용하는 것을 제안하였다. 먼저 밀집 벡터 기반의 검색 모델을 학습하고 학습된 모델로부터 고난도 부정(Hard negative) 지식 후보를 생성하고 주제어 기반 검색 방식으로 고난도 부정 지식 후보를 생성하여 각각 밀집 벡터 기반의 검색 모델을 학습하였다. 성능을 측정하기 위해 전체 지식 중에서 하나의 지식을 검색했을 때 정답 지식인 경우를 계산하였고 고난도 부정 지식 후보로 학습한 주제어 기반 검색 모델의 성능이 6.175%로 가장 높은 것을 확인하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1307-1312
• /
• 2004

Word sense disambiguation is one of the most important problems in natural language processing research topics such as information retrieval and machine translation. Many approaches can be employed to resolve word ambiguity with a reasonable degree of accuracy. These strategies are: knowledge-based, corpus-based, and hybrid-based. This paper pays attention to the corpus-based strategy. The purpose of this paper is to compare three famous machine learning techniques, Snow, SVM and Naive Bayes in Word-Sense Disambiguation on Thai language. 10 ambiguous words are selected to test with word and POS features. The results show that SVM algorithm gives the best results in solving of Thai WSD and the accuracy rate is approximately 83-96%.

• 한국디지털정책학회:학술대회논문집
• /
• 2004.11a
• /
• pp.405-421
• /
• 2004

The digital government is one of the most significant areas of study to emerge in information science in the past several years. The digital government is, in broad terms, a computerized system that allows a community of users to obtain a coherent means of access to an organized, electronically stored repository of information and knowledge. The information resources and technologies embodied by the World Wide Web are now accepted ad the primary example of the digital government. The need exists for a means to measure user success in the digital government. Because a digital government environment involves two broad functions?1) information search and retrieval and 2) interactivity with and through the medium-this research posits that measures of both of these functions will show positive correlation with user success.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10c
• /
• pp.307-312
• /
• 2006

멀티미디어의 비중이 커짐에 따라 컴퓨터 과학 각 분야에서 독자적인 기술들을 이용하여 실제 응용 및 시스템을 구축하고 있다. 하지만 멀티미디어 동영상 내에서 객체의 행위 단독적인 움직임을 수치로만 표현하여 자료를 처리함에 따라 의미를 해석하는 것이 부자연스럽고 정확한 숫자에 부합하는 행동의 검출이 어렵다. 본 논문에서는 멀티미디어 동영상의 기본적인 행위를 추출하고 이를 추상화, 정형화하여 보다 상위단계로 접근을 유도하여 멀티미디어 데이터에 대한 접근을 용이하게 하기위한 방법에 대하여 논의하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06c
• /
• pp.347-350
• /
• 2007

멀티미디어 데이터 처리 요구가 증가함에 따라 이의 의미적 표현 및 검색에 관한 연구가 활발히 이루어지고 있다. 최근에는 특히 지식 기반의 온톨로지를 이용한 의미적 검색에 초점을 두고 있으며, 구축된 온톨로지를 기반으로 동의어 관계, 반의어 관계 등을 이용하여 질의 확장으로 활용되고 있다. 하지만 이들은 대부분 속성 관계 등을 고려하지 않을 뿐만 아니라 각 관계별 가중치를 고려하지 않고 있다. 이에 본 논문에서는 비디오의 의미적 특징들을 추출하여 온톨로지를 구축한 후 의미 기반 검색을 위하여 관계별 가중치를 고려한 유사성 측정을 제안하고자 한다.

• Journal of the Korean Society for information Management
• /
• v.5 no.1
• /
• pp.131-152
• /
• 1988

It is purposed in this paper to improve the retrieval cffect~venebs through the use of the seman-- t r knowledge of search terms in a computerbased search system. This study is developed it1 three stages include the experimentation of index terms or1 the probab~listir model, indexing with relational operators, and knowledgebase design. The sl~bject experimerltrd is the specific fklds of Chemical Engineering, ' Fluid Flow' and 'Combustion: As for the system ~rnplementatlon. two kinds of search method a r e done. Orie is to search terms related to one specialty word, the other is to retriele the articles based or1 the gueries.