• Journal of Contemporary Eastern Asia
• /
• 제11권1호
• /
• pp.1-20
• /
• 2012

This study analyzes messages from Korean TV debates on the conflict over U.S. beef imports and the process of negotiations over the imports in 2008. The authors have conducted a content analysis and a semantic network analysis by using KrKwic and CONCOR. The data was drawn from nine TV debates aired by three major TV networks in Korea (MBC, KBS, and SBS) from 27 April 27 2008 to 6 July 2008. The results indicate substantial differences in the semantic structure between arguments by the government and those by civic groups. We also investigated the relationship between the terms frequently used by both sides (i.e., the government and civic groups), and the terms used exclusively by one side. There was a gradual increase in the number of terms frequently used by both sides over time, from the formation of the conflict to its escalation to its resolution. The results indicate the possibility of general agreement in conflict situations.

• 디지털융복합연구
• /
• 제12권6호
• /
• pp.245-252
• /
• 2014

시맨틱 검색은 논리적으로 표현된 지식 베이스를 사용하여 현재의 키워드 기반 검색보다 더 정확한 결과를 제공할 수 있다. 그러나 일반 사용자는 지식 기반의 복잡하고 정형화된 질의어와 스키마를 잘 알지 못한다. 그래서 검색 시스템은 사용자 키워드의 의미를 해석할 수 있어야 한다. 본 논문에서는 멀티미디어 콘텐츠의 시맨틱 검색을 위한 사용자 질의 의미 해석 시스템을 설명한다. 제안한 시스템은 도메인 온톨로지 기반으로 구축된 지식 베이스의 정형화된 구조에 의미 해석 과정이 통합된 온톨로지 지식 베이스 기반 검색 시스템이다.

• 한국전자거래학회지
• /
• 제12권3호
• /
• pp.151-175
• /
• 2007

지금까지 시맨틱 웹 서비스 발견은 WSMO나 OWL-S의 프로파일을 이용하여 수행되어 왔다. 그러나 이 연구들은 서비스의 이름과 input/output만을 이용하여 검색함으로써, 배송 후 지불을 하는 도서 판매 서비스를 찾아라.' 와 같이 서비스의 내부 정보에 대한 질의를 수행할 수 없다. 본 논문에서는 이러한 문제를 해결하기 위해 TM-S 온톨로지와 TMS-QL을 제시한다. TM-S 온톨로지는 프로세스 정보를 이용하여 서비스의 행동을 기술하며, 3가지 하위 온톨로지인 프로세스 시그니처 온톨로지, 프로세스 구조 온톨로지, 프로세스개념 온톨로지로 구성되어 있다. TMS-QL은 사용자가 TM-S 온톨로지에 대해 질의 요구를 기술할 수 있는 언어를 제공한다.

• 인지과학
• /
• 제10권3호
• /
• pp.1.1-10
• /
• 1999

한국어 명사들을 의미별로 분류하여 계층화시킨‘한국어 명사 의미 계층 구조’는, 한국어 문장을 처리할 때 의미 정보를 제공할 수 있는 매우 중요한 것들 중의 하나이다. 본 논문에서는, 국어 사전의 명사에 대한 뜻 풀이말을 이용하여 bottom-up 방식으로‘한국어 명사 의미 계층 구조’를 구축하였다. 본 논문에서 구축한‘한국어 명사 의미계층 구조’는, 트리(tree)가 43개, 중간 노드(node)가 2,443개, 단말 노드(terminal node)가 10,347개이며, 깊이(depth)가 17인 하나의 포리스트(forest)를 이룬다. 이것의 제 1, 2 계층(level 1, 2)에서의 분류 형태는 top-down 방식에 의한 기존의 분류들과 매우 다른 모습인 반면에, 제 3 이하의 계층들은 상당히 객관적이 형태를 이루고 있다.

• 문화기술의 융합
• /
• 제4권1호
• /
• pp.129-137
• /
• 2018

본 연구는 그간 학문적, 이슈적 관심에서 간과되었던 "대통령 지시사항"에 대한 분석을 수행하였다. 이러한 분석을 통해 대통령의 행정부처 내에서 진행되었던 정책방향의 차이에 대한 이해를 제고시키고, 시대의 흐름을 이해하는데 기여할 뿐만 아니라 향후 정책발굴에 있어서도 도움이 될 수 있음을 확인할 수 있었다. 본 연구는 대통령 지시사항과 관련한 키워드 네트워크 구조에 대한 패턴변화를 의미연결망 분석을 통해 고찰함으로써 대통령의 정책방향 차이가 대통령의 의지와 제도적 맥락 간의 상호작용에 연동되고 있다는 시사점을 제공하는데 기여하고 있다.

• 한국정보과학회논문지:데이타베이스
• /
• 제32권6호
• /
• pp.585-592
• /
• 2005

시맨틱 웹은 차세대 웹으로 연구되고 있으며 시맨틱 웹 상에서는 사람이 아닌 컴퓨터가 이해할 수 있는 정보를 처리해야 한다. 이러한 웹 자원의 내용을 기술하기 위해 온톨로지(Ontology)들을 이용한다. 이러한 온톨로지 중에 현재 W3C에서 제안한 OWL이 부각되고 있다. OWL을 처리하는 데이타 베이스에서 데이타는 그래프 형태로 저장되어 그래프 탐색을 통해 질의 처리를 수행한다. 본 논문에서는 OWL 데이타를 효율적으로 처리하기 위하여 시그니처를 이용한 최적화 기법을 제안한다. 논문에서 제안한 최적화 기법은 질의 수행 시 각 노드의 탐색 회수를 줄여 질의 수행을 빠르게 할 수 있게 한다.

• 대한건축학회연합논문집
• /
• 제21권5호
• /
• pp.109-116
• /
• 2019

The Seoul city recommended that old apartments be preserved, and as part of that, it decided to preserve some of the buildings for Jamsil Jugong, which was built in 1977, and Gaepo Jugong, which was constructed in 1981. The purpose of this study was to compare and review newspaper articles with two perspectives positive and negative about how the social perception of 'apartment trace remaining' was being constructed. By looking at the meaning of keywords delivered by newspaper articles and the interaction structure between keywords through the analysis of semantic networks, we analyzed how the media is pursuing an issue on the topic of preservation of architectural cultural heritage. The analysis results confirmed that there was a clear difference between positive and negative newspaper. Positive articles dealt with utilization from the point of view of keywords linked to preservation, and negative articles showed that keywords related to the property and backlash of residents linked to the policy of the Seoul Metropolitan Government were linked, leading to high negative public opinion.

• International Journal of Computer Science & Network Security
• /
• 제23권9호
• /
• pp.120-128
• /
• 2023

In this work, we have presented ATSA, a hierarchical attention deep learning model for Arabic sentiment analysis. ATSA was proposed by addressing several challenges and limitations that arise when applying the classical models to perform opinion mining in Arabic. Arabic-specific challenges including the morphological complexity and language sparsity were addressed by modeling semantic composition at the Arabic morphological analysis after performing tokenization. ATSA proposed to perform phrase-chunks sentiment embedding to provide a broader set of features that cover syntactic, semantic, and sentiment information. We used phrase structure parser to generate syntactic parse trees that are used as a reference for ATSA. This allowed modeling semantic and sentiment composition following the natural order in which words and phrase-chunks are combined in a sentence. The proposed model was evaluated on three Arabic corpora that correspond to different genres (newswire, online comments, and tweets) and different writing styles (MSA and dialectal Arabic). Experiments showed that each of the proposed contributions in ATSA was able to achieve significant improvement. The combination of all contributions, which makes up for the complete ATSA model, was able to improve the classification accuracy by 3% and 2% on Tweets and Hotel reviews datasets, respectively, compared to the existing models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권10호
• /
• pp.2718-2731
• /
• 2023

This paper presents a method of using syntax and shallow semantic analysis for Vietnamese question generation (QG). Specifically, our proposed technique concentrates on investigating both the syntactic and shallow semantic structure of each sentence. The main goal of our method is to generate questions from a single sentence. These generated questions are known as factoid questions which require short, fact-based answers. In general, syntax-based analysis is one of the most popular approaches within the QG field, but it requires linguistic expert knowledge as well as a deep understanding of syntax rules in the Vietnamese language. It is thus considered a high-cost and inefficient solution due to the requirement of significant human effort to achieve qualified syntax rules. To deal with this problem, we collected the syntax rules in Vietnamese from a Vietnamese language textbook. Moreover, we also used different natural language processing (NLP) techniques to analyze Vietnamese shallow syntax and semantics for the QG task. These techniques include: sentence segmentation, word segmentation, part of speech, chunking, dependency parsing, and named entity recognition. We used human evaluation to assess the credibility of our model, which means we manually generated questions from the corpus, and then compared them with the generated questions. The empirical evidence demonstrates that our proposed technique has significant performance, in which the generated questions are very similar to those which are created by humans.

• International Journal of Advanced Culture Technology
• /
• 제12권1호
• /
• pp.227-233
• /
• 2024

This study was conducted to understand the essential structure and meaning of the experience of participating in the Jigsaw class designed to achieve the learning goals for nursing students with different basic learning abilities, and to prepare a plan for each individual to learn as a collaborator rather than a competition with each other. As a study based on Giorgi's phenomenological research method and in-depth interviews, data collection was collected from 10 study participants from December 1, 2023 to December 20, 2023. The main question used in the interview was "What impressed you after participating in Jigsaw teaching meathod?" The transcribed data were analyzed through the stages of overall recognition, classification of semantic units, transformation of semantic units into psychological expressions, and integration into general structures according to Giorgi's qualitative analysis method. As a result, a total of 89 semantic units, 35 essential psychological meanings, 13 sub-components, and 6 components were derived. The six components include 'good communication', 'difference appear in material preparation', 'easy to understand', 'finding team members who form a learning atmosphere well', 'A talkative class', and 'Unprepared team members are uncomfortable'. Based on the above results, it is expected that students in a passive position in class will become teachers themselves, take responsibility for preparing for learning, and provide useful basic data for developing programs that cooperate among students.