• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.409-414
• /
• 2023

최근 지식 기반 대화 생성에 많은 연구자가 초점을 맞추고 있다. 특히, 특정 도메인에서의 작업 지향형 대화 시스템을 구축하는 것은 다양한 도전 과제가 있으며, 이 중 하나는 거대 언어 모델이 입력과 관련된 지식을 활용하여 응답을 생성하는 데 있다. 하지만 현재 거대 언어 모델은 작업 지향형 대화에서 단순히 정보를 열거하는 방식으로 응답을 생성하는 경향이 있다. 이 논문에서는 전문 지식과 대화 정책 예측 모델을 결합한 프롬프트를 제시하고 작업 지향형 대화에서 사용자의 최근 입력에 대한 정보 제공 및 일상 대화를 지원하는 가능성을 탐구한다. 이러한 새로운 접근법은 모델 파인튜닝에 비해 비용 측면에서 효율적이며, 향후 대화 생성 분야에서 발전 가능성을 제시한다.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.3 no.3
• /
• pp.77-89
• /
• 2000

The purpose of this study is to establish a Zone-Based Land Use Information System(ZBLIS) using digital topographic maps and public statistics data with a case for Pohang. The Basic Spatial Units(BSUs) used in ZBLIS is the administrative district units(Dong and Lie), and larger or smaller spatial units than this are brought out from BSUs. In the first step, the structure of ZBLIS is constructed to choose Analysis Zone on the top menu, and in subsequent steps, to choose Analysis Categories on sub-menu in terms of dialog windows, and then to choose Analysis Sub-categories and Analysis Theme. The 11 Analysis Categories are consisted of Population, Land Use, Transportation, Industry and Economy etc.. In this case study, it is found that there occur some technical problems in the process of making base-map from digital topographic maps, and inputting attribute data to this base map. For each of these problems, some handling method are recommended.

• Journal of The Korean Association of Information Education
• /
• v.9 no.2
• /
• pp.243-254
• /
• 2005

Along the information technology progresses, the demand for the educational application increases which derives the need for cyber education. Cyber education should take the knowledge construction model rather than the knowledge delivery model. For the educational paradigm shift by cyber education, 'Project-Based Learning' and 'Cyber Learning Community' need to be adopted. In this study, project-based cyber learning community for teacher education is developed with 5 major categories: Home(community vision, general information, project list, Q&A), project learning center(preparation for the instructional activities, group-based learning activities, presentations), meeting plaza(request for group mentoring, sharing ideas, meeting specialist, survey participating, forum participating, result presentation), references(cases of project studies, materials for project studies, materials for teacher education, general materials), management(project management, project cases, idea bank, finding partners, dialog with instructors, sharing references, sharing experiences, survey, forum).

• Journal of the Korean Society for Library and Information Science
• /
• v.19
• /
• pp.189-241
• /
• 1990

This study identified cognitive styles of online searchers in terms of Field Dependence (FD) and Field Independence (FI) dimension and determined whether searching performance was affected by FD / FI cognitive differences between online searchers and the extent to which searching performance was affected by the FD / FI dimension of cognitive style. This study used a quasi experimental design with 41 student subjects using the Lockheed DIALOG system and ERIC ONT AP database. Cognitive styles of student subjects were measured by using GEFT (Group Embedded Figure Test) and the subjects were divided into two cognitive groups- FD and FI based on the GEFT scores. Each subject was assigned two predetermined searches which had different search goals-a 'high precision search' and a 'high recall search.' Search performance of the two cognitive groups on the two problems was compared in order to see how these two groups responded to achieving different search goals in terms of search strategy, search inputs, and resulting search outputs. The major findings of this study were: 1. The pattern of approaching a search problem regardless of whether it was a high precision search or a high recall search was not significantly different between the two cognitive groups. 2. The FI group tended to use significantly more terms for the high recall search than the FD group but slightly less time than the FD group. However, significant differences in connect time between the two groups were not revealed. 3. For both search problems the FI group achieved a significantly higher success rate than the FD group. The FI group were significantly more successful searchers than the FD group. As for unit / cost, although the FI group were more cost effective than those of the FD group for both searches, these differences were too small to be statistically significant. 4. Mean differences of the search performance variables between the FD / FI groups were consistent across the two types of search questions. The FI group seemed to be equally effective for both types of search questions. In conclusion, the differences found in number of terms used and success rate between the two cognitive groups apparently resulted from different cognitive styles.

• Journal of Korea Multimedia Society
• /
• v.7 no.10
• /
• pp.1452-1463
• /
• 2004

The requirement of automatic video summary is increasing as bi-directional broadcasting contents and various user requests and preferences for the bi -directional broadcast environment are increasing. Automatic video summary is needed for an efficient management and usage of many contents in service provider as well. In this paper, we propose a method to generate a content-based summary of linguistic educational videos automatically. First, shot-boundaries and keyframes are generated from linguistic educational video and then multiple(low-level) visual features are extracted. Next, the semantic parts (Explanation part, Dialog part, Text-based part) of the linguistic educational video are generated using extracted visual features. Lastly the XMI- document describing summary information is made based on HieraTchical Summary architecture oi MPEG-7 MDS (Multimedia I)escription Scheme). Experimental results show that our proposed algorithm provides reasonable performance for automatic summary of linguistic educational videos. We verified that the proposed method is useful ior video summary system to provide various services as well as management of educational contents.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.28 no.6
• /
• pp.114-126
• /
• 2001

The purpose of this study is to establish the databases of pollutant sources and water quality measurement data by utilizing GIS, and making the user interface for the management of pollutant sources. Yeongsan Estuarine Lake was formed of a huge levee of 4.35 km constructed by an agricultural reclamation project. Water quality of the reservoir has been degraded gradually, which mainly attributes to increase of point and non-point source pollutant loads from the lake's watershed of 33,374.3 $\textrm{km}^2$ into it. Application of GIS to establishment of the database was researched of pint source such as domestic sewage, industrial wastewater, farm wastes, and fishery wastes, and non-pont source such as residence, rice and upland field, and forest runoffs of the watershed of the lake. NT Acr/Info and ArcView were mainly utilized for the database formation. Land use of the watershed using LANDSAT image data was analyzed for non-point source pollutant load estimation. Pollutant loads from the watershed into the reservoir were calculated using the GIS database and BOD, TN, TP load units of point and non-point sources. Total BOD, TN, TP loads into it reached approximately to 141, 715, 2,094 and 4,743 kg/day respectively. The loads can be used as input parameters for water quality predicting model of it. A user-friendly interface program was developed using Dialog Designer and Avenue Script of AcrView, which can perform spatial analysis of point and non-point sources, calculate pollutant inputs from the sources, update attribute data of them, delete and add point sources, identify locations and volumes of water treatment facilities, and examine water quality data of water sampling points.

• The Journal of the Korea Contents Association
• /
• v.10 no.9
• /
• pp.9-17
• /
• 2010

Nowadays, many research have been conducted on robots or interactive characters that properly respond to the users affection. In this paper, we develop an intelligent messenger that provides appropriate responses to text inputs according to user's intention and affection. In order to properly respond, the intelligent messenger adapts methods to recognize user's speech act and affection. And it uses an AIML-based interactive script to which tags are additionally attached to express affection and speech act. If the intelligent messenger finds a proper reply in the interactive scripts, it displays the reply in a dialog window, and an animation character expresses emotion assimilated with a user's affection. If the animation character is synchronized with a content robot through a wireless link, the robot in the same space with the user can provide emotional response.

• The Journal of the Korea Contents Association
• /
• v.13 no.12
• /
• pp.626-637
• /
• 2013

Film sound should be analyzed based upon the profound understanding of sound design process and the principle behind it. Lack of this knowledge prevents the research from having the comprehensiveness and concreteness. This study aims to reaffirm the important role of sound design in filmmaking while also investigating the narrative functions of sound design. The role of sound design as a cinematic technique was defined as creating audio-visual experience with a collection of information, emotion, and ideas organized and presented in the sound narrative of films. Each process of sound design, dialog, ambience, Foley, and sound effects, was proved to be performing this role as a result of a case study of various narrative films. The narrative functions of sound design was able to be defined as well.

• KIISE Transactions on Computing Practices
• /
• v.22 no.1
• /
• pp.50-55
• /
• 2016

To attain an understanding of customers' opinions or demands regarding a companies' products or service, it is important to consider VOC (Voice of Customer) data; however, it is difficult to understand contexts from VOC because segmented and duplicate sentences and a variety of dialog contexts. In this article, POS (part of speech) and morphemes were selected as language resources due to their semantic importance regarding documents, and based on these, we defined an LSP (Lexico-Semantic-Pattern) to understand the structure and semantics of the sentences and extracted summary by key sentences; furthermore the LSP was introduced to connect the segmented sentences and remove any contextual repetition. We also defined the LSP by categories and classified the documents based on those categories that comprise the main sentences matched by LSP. In the experiment, we classified the VOC-data documents for the creation of a summarization before comparing the result with the previous methodologies.

• Journal of Advanced Navigation Technology
• /
• v.12 no.2
• /
• pp.91-99
• /
• 2008

In this paper, we implemented an wireless remote control and monitoring system by using Globalstar satellite modem. This system is composed of the data terminal equipment of Globalstar data communication system using microcontroller, C8051F023, and WGIS(Web-based GIS) user program. We tested the wireless remote control and monitoring system with data terminal equipment and user program how to work properly, and verified that the user could confirm the data from the data terminal equipment, which can provide the status of input/output devices and the information of location with the main and control dialog by GIS(Geographic Information System) program. For data communication of between data terminal equipment and user program, we programed PPP and TCP/IP protocol to communicate with each other. Some GIS tools used in this program are ArcView and MapObject from ESRI to offer various visual mapping information to the user.