• Korean Institute of Interior Design Journal
• /
• v.16 no.6
• /
• pp.65-76
• /
• 2007

This research is progressed on the premise that there is a basic rule to organize a space in form generation process. In this study first, antecedent researches are inquired, and formal vocabularies related with form generation in space design are founded. Generally in the organizing process of spatial form designer could have selectively combined formal vocabularies consciously or unconsciously, and these formal vocabularies related with form generation are classified with 'formal elements' and 'spatial relationships'. First, as formal elements '2-dimensional line elements(rectilinear, oblique-linear, curvilinear)' are chosen. Second, formal vocabularies of 'spatial relationships' are 37 extracted from literatures related with architectural language or spatial language. Among them there are several vocabularies with similar or same meaning, they are unitized to representative one. Thereupon 20 vocabularies are finally selected as the formal vocabularies of 'spatial relationships', they are addition, subtraction, intersection, superimposition, juxtaposition, shifting, rotation, reflection, scaling, stretching, shear, bending, folding, distortion, articulation, deconstruction, symmetry, repetition, proportion, and asymmetry.

• International Journal of Contents
• /
• v.1 no.2
• /
• pp.39-43
• /
• 2005

In this paper, we describe a generation mechanism of semantic-based queries for high accuracy information retrieval and question answering. It is difficult to offer the correct retrieval result because general information retrieval systems do not analyze the semantic of user's natural language question. We analyze user's question semantically and extract semantic features, and we .generate semantic-based queries using them. These queries are generated using the se-mantic-based question analysis grammar and the query generation rule. They are represented as semantic features and grammatical morphemes that consider semantic and syntactic structure of user's questions. We evaluated our mechanism using 100 questions whose answer type is a person in the TREC-9 corpus and Web. There was a 0.28 improvement in the precision at 10 documents when semantic-based queries were used for information retrieval.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.3
• /
• pp.45-55
• /
• 2008

Due to the increasing complexity of embedded system design, automatic code generation of embedded software and hardware-software co-design methodologies are gaining great interest from industries and academia. Such an automatic design methodologies are always demanding a formal system specification languages for defining designer's idea clearly and precisely. In this paper, we propose automatic embedded C code generation from SDL (Specification and Description Language, ITU-T recommended the SDL as a standard system description language) with considering a real-time uC/OS-II operating system. Our automatic embedded C code generator is expected to provide a fast specification, verification and performance evaluation platform for embedded software designs.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.39 no.5
• /
• pp.32-44
• /
• 2002

In this paper, we propose TV caption-based KSL(Korean Sign Language) generation system. Through TV caption decoder, this caption signal is transmitted to PC. Next, caption signal is segmented into meaning units by morphological analyzer in considering specific characteristics of Korean sign language. Finally, 3D KSL generation system represents the transformed morphological information by 3D visual graphics. Specifically, we propose a morphological analyzer with many pre-processing techniques for real-time capability. Our developed system is applied to real TV caption program. Through usage of the deaf, we conclude that our system is sufficiently usable compared to conventional TV caption program.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.8
• /
• pp.385-390
• /
• 2017

Because of the ever-increasing software complexity, model-based development techniques are becoming an essential technique in software development. However, even if model-based techniques are used, the test case generation for complex software is still a challenge to solve. In this paper, we propose a method to generate automatic test cases based on UML model using custom parser and SMT solver. By proposed technique, a test case can be generated even though the model is described in a platform independent language such as action language, or in a platform dependent language. In addition, a concolic execution technique is applied to efficiently generate test cases in the model. In this paper, we present a case study on the power window switch model of Hyundai Santa Fe through the proposed test case generation technique.

• The Journal of the Korea Contents Association
• /
• v.9 no.2
• /
• pp.152-162
• /
• 2009

At present, Authoring tools, which are used to develop the WIPI applications are less convenient to be coded. Usually, the programming tools only focus on the grammar while scarcity of visualization. Developer forced directly codes all times during the development by this cause. As a procedure for rapid WIPI Application Development, in this paper, WIPI API High Level Component is first visualized, in order words, graphic control is developed. Second this control is used in designing the mobile layout. Then UI Markup Language and source code can be generated automatically. With this view, we propose the JIML(Jlet Interface Markup Language) with UI Markup Language based XML of WIPI Jlet Platform and also present the transformable rule for generation to the WIPI code about WIPI Jlet UI from offered JIML. Also we implement the WIPI Jlet Generation System to make the generation to JIML, WIPI code. The Implemented System provides efficiency when developing WIPI Business Application, and helps to enable rapid development.

• Journal of Contemporary Eastern Asia
• /
• v.17 no.1
• /
• pp.27-49
• /
• 2018

Public Diplomacy (PD) is the third pillar of South Korean foreign policy. According to the Ministry of Foreign Affairs, PD aims to attract foreign audiences by means of art, knowledge transmission, media, language and foreign aid. When it comes to the Korean language, its global profile has seen an especially marked increase in recent years (Kim, 2009). Thus, this paper's objective is to explain the relevance of the Korean language in the generation of South Korea's soft power. I draw from $C{\acute{e}}sar$ Villanueva's reflections in order to problematize how language promotion can be translated into soft power at five different levels: the empathetic, the sympathetic, the geopolitical, the diplomatic and the utilitarian. I observe that in the case of the Korean language in Mexico City, soft power has the potential to be generated on three levels: it helps to increase knowledge of Korean culture (empathetic); it exercises symbolic persuasion (geopolitical), since the products of cultural industries are mostly in Korean; and it is used as a tool for economic transactions in Mexico City (utilitarian).

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.315-320
• /
• 2019

질문 생성이란 구절이 입력되면 구절에서 답을 찾을 수 있는 질문을 자동으로 생성하는 작업으로 교육용 시스템, 대화 시스템, QA 시스템 등 다양한 분야에서 중요한 역할을 한다. 질문 생성에서 정답의 단어가 질문에 포함되는 문제점을 해결하기 위해 구절과 정답을 분리한다. 하지만 구절과 정답을 분리하게 되면 구절에서 정답의 정보가 손실되고, 정답에서는 구절의 문맥 정보가 손실되어 정답 유형에 맞는 질문을 생성할 수 없는 문제가 발생된다. 본 논문은 이러한 문제를 해결하기 위해 분리된 정답과 구절의 정보를 연결시켜주는 정답과 구절의 공동 주의 집중 계층을 제안한다. 23,658개의 질문-응답 쌍의 말뭉치를 이용한 실험에서 정답과 구절의 공동 주의 집중 계층이 성능 향상에 기여해 우수한 성능(BLEU-26.7, ROUGE-57.5)을 보였다.

• Electronics and Telecommunications Trends
• /
• v.39 no.1
• /
• pp.95-105
• /
• 2024

In natural language processing, large language models such as GPT-4 have recently been in the spotlight. The performance of natural language processing has advanced dramatically driven by an increase in the number of model parameters related to the number of acceptable input tokens and model size. Research on multimodal models that can simultaneously process natural language and image data is being actively conducted. Moreover, natural-language and image-based reasoning capabilities of large language models is being explored in robot artificial intelligence technology. We discuss research and related patent trends in robot task planning and code generation for robot control using large language models.

• Korean Journal of Cognitive Science
• /
• v.20 no.4
• /
• pp.421-437
• /
• 2009

A chatting system is a computer program that simulates conversations between a human and a computer using natural language. In this paper, we propose a statistical model to generate natural chatting sentences when keywords and speech acts are input. The proposed model first finds Eojeols (Korean spacing units) including input keywords from a corpus, and generate sentence candidates by using appearance information and syntactic information of Eojeols surrounding the found Eojeols. Then, the proposed model selects one among the sentence candidates by using a language model based on speech act information, co-occurrence information between Eojeols, and syntactic information of each Eojeol. In the experiment, the proposed model showed the better correct sentence generation rate of 86.2% than a previous conventional model based on a simple language model.