• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.4
• /
• pp.275-287
• /
• 2024

Research on the integration of Knowledge Graphs (KGs) and Language Models (LMs) has been consistently explored over the years. However, studies focusing on the automatic generation of text using the structured knowledge from KGs have not been as widely developed. In this study, we propose a methodology for automatically generating specific domain-related research items (Related Work) at a level comparable to existing papers. This methodology involves: 1) selecting optimal prompts, 2) extracting triples through a four-step refinement process, 3) constructing a knowledge graph, and 4) automatically generating related research. The proposed approach utilizes GPT-4, one of the large language models (LLMs), and is desigend to automatically generate related research by applying the four-step refinement process. The model demonstrated performance metrics of 17.3, 14.1, and 4.2 in Triple extraction across #Supp, #Cont, and Fluency, respectively. According to the GPT-4 automatic evaluation criteria, the model's performamce improved from 88.5 points vefore refinement to 96.5 points agter refinement out of 100, indicating a significant capability to automatically generate related research at a level similar to that of existing papers.

• The KIPS Transactions:PartD
• /
• v.12D no.6 s.102
• /
• pp.849-856
• /
• 2005

As XML is more proliferate as a data type between internet programs, automatic generation methods of user input form interfaces get more attention. Recently, generating user interfaces for web application or web service clients become very popular. In this paper, we study the method of automatic generation for XForms-based user interface codes based on XML structure definitions in DTD. With the repetitive edit action model, we present a formal generation method of Input form codes and the overall user interface pages. For the generated code is using XForms as a target language, the result is clear and efficient with the MVC structure. Also, we have developed XFormsGen system which implements the proposed method over the Orbeon presentation server.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.32 no.9
• /
• pp.41-48
• /
• 2004

In this work, a domain-wise hash structure is developed for efficient data handling, and by using the developed domain-wise hash structure, an automatic triangular mesh generation algorithm is proposed. To generate the optimal nodal points and triangles efficiently, the advancing layer method and Delaunay triangulation method are utilized. To investigate the performance of the proposed algorithm, benchmarking tests are carried out for various models including convex, concave and complicated shapes through the developed object oriented C++ mesh generation code.

• Annual Conference on Human and Language Technology
• /
• 2007.10a
• /
• pp.107-113
• /
• 2007

본 연구는 시맨틱 데이터 정합성 검사와 RDF 트리플 생성 기능을 가진 URI 서버 내 DB 스키마의 자동 생성 방안을 기술한다. URI 서버는 시맨틱 웹 기술 기반 프레임워크 구성에 필요한 핵심 엔진으로서 인스턴스 생성 관리기, 검색 엔진, 추론 엔진 등과의 상호 작용을 통해 시맨틱 데이터를 서비스한다. 도메인이 바뀌거나 서비스가 변경되는 경우 DB 스키마를 전문가에 의해 수작업으로 생성함으로써 서비스 환경 변화에 즉각 대응하지 못하는 문제점을 가진 기존 URI 서버를, 적재되는 온톨로지에 따라 DB 스키마를 동적으로 자동 생성하는 방식으로 변경함으로써 다양한 응용 분야와 도메인에의 높은 이식성(Portability)을 보장할 수 있도록 한다. 기반정보 온톨로지, 응용 온톨로지, 개인화 온톨로지 등 3개 온톨로지 스키마와 11만 건 이상의 Citeseer Open Access Metadata로부터 추출된 인스턴스를 대상으로 한 실험을 통해 URI 서버 내 DB 스키마 자동 생성 가능성을 실증하였다.

• The KIPS Transactions:PartD
• /
• v.14D no.2
• /
• pp.191-202
• /
• 2007

In general, test data generation techniques require the specification of an entire program path for automated test data generation. This paper presents a new way for generating test data automatically een without specifying a program path completely. For the ends, this paper presents a technique for transforming a program under test into Alloy which is the first order relational logic and then producing test data via Alloy analyzer. The proposed method reduces the burden of selecting a program path and also makes it easy to generate test data according to various test adequacy criteria. This paper illustrates the proposed method through simple, but illustrative examples.

• The KIPS Transactions:PartD
• /
• v.16D no.3
• /
• pp.371-380
• /
• 2009

Recently, lots of research on automated test data generation has been actively done. However, techniques for automated test data generation presented so far have been proved ineffective for programs with flag variables. It can present problems when considering embedded systems such as engine controllers that make extensive use of flag variables to record state information concerning devices. This paper introduces a technique for generating test data effectively for programs with flag variables. The presented technique transforms the test data generation problem into a SAT(SATisfiability) problem and makes advantage of SAT solvers for automated test data generation(ATDG). For the ends, we transform a program under test into Alloy which is the first-order relational logic and then produce test data via Alloy analyzer.

• Proceedings of the KAIS Fall Conference
• /
• 2002.11a
• /
• pp.149-151
• /
• 2002

본 논문에서는 유한요소를 자동으로 생성하는 프로그램을 구현하였다. Delaunay 삼각화이론을 적용하여 요소를 생성하였고 요소의 생성 속도를 개선하기 위해서 로손(Laswson)의 찾기 알고리즘을 적용하였다. 요소의 형상을 개선하고자 절점들을 효과적으로 배치하고 분할 한 후에 라플라스 조정을 통해 등변에 가까운 요소로 생성하였다. 본 논문에서 제시한 알고리즘의 검증을 위해 박막층을 가진 초고주파 소자를 선택하여 요소의 형상과 생성과정에서 검색회수를 비교하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.160-162
• /
• 2004

본 논문에서는 XML 문서간의 자동 변환을 위한 효율적인 XSLT 스크립트를 생성하는 알고리즘을 제안한다. 제안된 방법은 XML DTD를 구성하는 단말 노드간의 일대일 대응관계가 주어져 있다는 가정 하에 XSLT 스크립트를 생성하는데 중점을 둔다. 제안된 알고리즘은 상향식과 하향식의 복합적인 접근 방식을 적용한다. 먼저 중간 노드간의 대응관계를 상향식으로 생성하며 하향식 깊이 우선 탐색을 적용하여 XSLT 스크립트를 생성한다. 실험결과, 제안된 방법은 기존 연구와 비교하여 XML 문서를 보다 빠르게 변환하는 XSLT 스크립트를 생성하였다.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.36 no.7
• /
• pp.634-641
• /
• 2008

Automatic Differentiation(AD) is a tool for generating sensitivities, such as gradient or Jacobian, automatically. AD tools provide mathematically exact sensitivities for the given source code. In this paper applications of automatic differentiation are studied. Derivative codes are generated with AD tools for structural analysis code and flow analysis code. How to apply AD tools is explained and the accuracy of sensitivities is compared with the finite difference. Sensitivities of generated derivative code accord well with finite difference, but the calculation time of derivative code increases. It was found that the calculation time can be decreased by additional modification of derivative code.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.38 no.4
• /
• pp.277-284
• /
• 2001

Viterbi algorithm is widely used in digital communication system for FEC(forward error correction). Each communication systems based on the Viterbi algorithm use specific Viterbi decoder which has different code parameter values. Even if Viterbi decoder has the same code parameters, it can be varied by the design architecture adopted. We propose the parameterized VHDL model generator for the efficiency of the design. It makes it possible to achieve shorter design time and lower design cost. The model generator searches the design space available and finds out the optimal design point to generate a decoder model.