• Annual Conference on Human and Language Technology
• /
• 1997.10a
• /
• pp.341-346
• /
• 1997

개념기반 분석방법은 발화문에서 발화자가 전달하고자 하는 중요한 부분만을 추출하여 개념어로 대표하여 분석하기 때문에 문장에서 발생하는 불필요한 여러 언어현상을 무시하고 주요 의미만 추출할 수 있는 강건함을 가장 큰 장점으로 갖는다. 한국어는 영어권 언어와는 달리 교착어와 부분 자유 어순의 특징을 가지기 때문에 구문정보를 이용하지 않는 순수 개념 기반의 분석기법을 한국어에 그대로 적용하면 문법의 복잡도가 증가하여 시스템 성능이 크게 저하된다. 본 논문에서 제시하는 구문정보를 이용한 개념기반의 분석방법은 순수 개념 기반의 분석기법이나 구문정보만을 사용하는 방법보다 모호성이 적고, 문법의 기술이 용이하며, 대화체 처리의 어려운 점들을 상당수 극복할 수 있다. 또한 분석루틴의 skip기능은 자연 발화문의 분석률을 높여주며, 어근으로부터 분리한 어미를 일정한 개념으로 분류함으로써 교착어의 특성으로 인한 문법의 복잡도를 해소하였고, 분석문법으로 부분 자유 어순에 따른 다양한 문장들을 수용할 수 있다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2000.10a
• /
• pp.406-411
• /
• 2000

Currently, many kinds of multimedia Services are provided for users using internet and broadcasting infrastructure because of advanced technology Progression of network technology, digital communication and broadcasting technology. In future, Information technology might be important. Information retrieval, Information extraction technology and multimedia service framework standardization make it possible to extract necessary information from a great deal of information. And Interactive service and knowledge library also will provide user-friendly interface technology on soon. In this paper, we describe current standard technology, products and market trends.

• Korean journal of communication and information
• /
• v.44
• /
• pp.108-143
• /
• 2008

Candidate images refer to a holistic impression of a candidate which is composed of various dimensions of attributes. This study investigated how online and offline news media, campaign media such as political ads, televised debates, and candidate web-sites, and interpersonal political talk influenced voters' images of a candidate in such dimensions as personal traits, job-performance abilities, and policy capabilities, and further their political decision making in the 17th presidential election in Korea. The analysis focused on President Lee, Myung Bak who won the election by obtaining nearly 50% of the effective votes. According to the data analyses, first, uses of offline newspapers positively influenced voters' images of candidate Lee's personal traits such as his morality, integrity, trustworthiness, and compassion, yet online news uses had an opposite effect on voters' impression of his job-performance and economic policy capabilities. Secondly, among various campaign media, television ads and candidate web-sites positively contributed to the formation of candidate Lee's images, yet showed little direct effect on vote choice, indicating that campaign media mainly indirectly influenced voters' political decision making. Each of the first, second, and third televised candidate debates revealed unique effects on image formation and vote choice. Thirdly, the network size and frequency of political talk negatively influenced image formation regarding candidate Lee's personal traits and economic policy capabilities, yet the discussion network size positively contributed to the Lee votes. Forth, among various dimensions of candidate images, voters' perceptions of candidate Lee's personal traits appeared to be the most significant predictor of the support for him.

• Korean Journal of Culture and Social Issue
• /
• v.28 no.2
• /
• pp.83-106
• /
• 2022

The current study examined the effects of the type and context of self-talk on task performance, task-post emotion, and perceived stress. Participants were 100 undergraduates in Busan. Participants were randomly assigned to one of four the experimental groups that were set by combining the narrative condition (the first-person versus non-first-person) to the content condition (self-reinforcing versus self-critic) to measure their pre and post intervention responses. For the analysis, we performed two-ways analysis of variance using the difference value of dependent variables comparing the pre and post-intervention. As a result of the analysis, we found that content condition of self-talk significantly influenced task performance, task-related confidence, emotion response, and perceived stress. That is, the self-reinforcement self-talk group showed better performance, higher task-related confidence, more positive emotion, lower negative emotion and less perceived stress than the self-critic self-talk group. The contents conditions of self-talk interacted with the narrative condition of self-talk to predict perceived stress, indicating that only non-first person/self-reinforceing self-talk group showed reduced levels of perceived stress.

• Korea Petroleum Association Journal
• /
• no.4 s.110
• /
• pp.16-23
• /
• 1990

이 글은 지난 4월 4일 남북대화사무국 빌딩에서 열린 21세기 위원회(위원장 이관) 주최의 「환경과 자원세미나」에서 발표된 주제논문을 옮긴 것이다. <편집자 주>

• Science of Emotion and Sensibility
• /
• v.16 no.3
• /
• pp.281-292
• /
• 2013

The purpose of this study was to identify the effect of gesture and facial expression on persona effects. Fifty-six college students were recruited for this study, and non-verbal communication skills were applied to a pedagogical agent with gesture (conversational vs. deictic) and facial expression. The conversational gesture may have relationship with social interaction hypothesis of pedagogical agent while the deictic gesture may have relationship with attentional guidance hypothesis. The facial expression can be assumed to facilitate the social interaction between the pedagogical agent and learners. Interestingly, the conversational gesture group showed a tendency of outperforming the deictic gesture group. It may imply that the social interaction theory has a strong impact on cognitive support as well as social interaction for learners. There was a significant interaction effect on the engagement when both of facial expression and conversational gesture were applied. This result has two implications. First, facial expression can facilitate the persona effect for engagement.

• The Journal of the Korea Contents Association
• /
• v.7 no.2
• /
• pp.150-160
• /
• 2007

In the actual classroom the so-called flow learning is able to motivate the students through face-to-face feedback, and to meet their needs for educational achievement. By contrast, the so-called e-learning method falls short of the satisfactory level of real-life interaction, which makes many learners drop out or give up on their learning. In order to better the e-learning environment, this study presents a dialogue-based feedback system that improves the flow learning of the learners' in the classroom. This newly developed system was applied at the actual school. The result is that the experimented group improved its flow learning, compared with the controlled group. In the former group, each individual showed some consciousness of objective and challenge following the concrete feedback. That is to say, this system enhances the attitude of an active participation and induces the flow learning, thanks to the dialogue-based feedback and the sustained interest in learning. In conclusion, the significance of this study lies in suggesting the direction of a new learning method development in the e-learning environment.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.7
• /
• pp.834-839
• /
• 2005

When a great variety of services become available to user through the broadband convergence network in the ubiquitous home environment, an intelligent agent is required to deal with the complexity of services and perceive intension of a user. Different from the old-fashioned command-based user interface for selecting services, conversation enables flexible and rich interactions between human and agents, but diverse expressions of the user's background and context make conversation hard to implement by using either user-initiative or system-initiative methods. To deal with the ambiguity of diverse expressions between user and agents, we have to apply hierarchial bayesian networks for the mixed initiative conversation. Missing information from user's query is analyzed by hierarchial bayesian networks to inference the user's intension so that can be collected through the agent's query. We have implemented this approach in ubiquitous home environment by implementing simulation program.

• Smart Media Journal
• /
• v.13 no.8
• /
• pp.26-38
• /
• 2024

This paper discusses the use of GPT and GPT API for prompt engineering in the development of the interactive smart device lock screen application "Smart Lock," aimed at enhancing literacy among young children and lower-grade elementary and middle school students during critical language development periods. In an era where media usage via smartphones is widespread among children, smartphone-based media is often cited as a primary cause of declining literacy. This study proposes an application that simulates conversations with parents as a tool for improving literacy, providing an environment conducive to literacy enhancement through smartphone use. Generative AI GPT was employed to create literacy-improving problems. Using pre-generated data, situational dialogues with parents were presented, and prompt engineering was utilized to generate questions for the application. The response quality was improved through parameter tuning and function calling processes. This study investigates the potential of literacy improvement education using generative AI through the development process of interactive applications.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.219-240
• /
• 2023

Conversational AI which allows users to interact with satisfaction is a long-standing research topic. To develop conversational AI, it is necessary to build training data that reflects real conversations between people, but current Korean datasets are not in question-answer format or use honorifics, making it difficult for users to feel closeness. In this paper, we propose a conversation dataset (KOMUChat) consisting of 30,767 question-answer sentence pairs collected from online communities. The question-answer pairs were collected from post titles and first comments of love and relationship counsel boards used by men and women. In addition, we removed abuse records through automatic and manual cleansing to build high quality dataset. To verify the validity of KOMUChat, we compared and analyzed the result of generative language model learning KOMUChat and benchmark dataset. The results showed that our dataset outperformed the benchmark dataset in terms of answer appropriateness, user satisfaction, and fulfillment of conversational AI goals. The dataset is the largest open-source single turn text data presented so far and it has the significance of building a more friendly Korean dataset by reflecting the text styles of the online community.