• Proceedings of the KSPS conference
• /
• 2007.05a
• /
• pp.29-32
• /
• 2007

This paper describes a multimodal dialog system that uses Hidden Information State (HIS) method to manage the human-machine dialog. HIS dialog manager is a variation of classic partially observable Markov decision process (POMDP), which provides one of the stochastic dialog modeling frameworks. Because dialog modeling using conventional POMDP requires very large size of state space, it has been hard to apply POMDP to the real domain of dialog system. In HIS dialog manager, system groups the belief states to reduce the size of state space, so that HIS dialog manager can be used in real world domain of dialog system. We adapted this HIS method to Smart-home domain multimodal dialog system.

• Journal of Computing Science and Engineering
• /
• v.4 no.1
• /
• pp.1-22
• /
• 2010

A field of spoken dialog systems is a rapidly growing research area because the performance improvement of speech technologies motivates the possibility of building systems that a human can easily operate in order to access useful information via spoken languages. Among the components in a spoken dialog system, the dialog management plays major roles such as discourse analysis, database access, error handling, and system action prediction. This survey covers design issues and recent approaches to the dialog management techniques for modeling the dialogs. We also explain the user simulation techniques for automatic evaluation of spoken dialog systems.

• Annual Conference on Human and Language Technology
• /
• 2008.10a
• /
• pp.156-161
• /
• 2008

This work presents an agenda-based approach to improve the robustness of the dialog manager by using dialog examples and n-best recognition hypotheses. This approach supports n-best hypotheses in the dialog manager and keeps track of the dialog state using a discourse interpretation algorithm with the agenda graph and focus stack. Given the agenda graph and n-best hypotheses, the system can predict the next system actions to maximize multi-level score functions. To evaluate the proposed method, a spoken dialog system for a building guidance robot was developed. Preliminary evaluation shows this approach would be effective to improve the robustness of example-based dialog modeling.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.1
• /
• pp.17-24
• /
• 2018

With improvement of speech recognition and natural language processing, dialog systems are recently adapted to various service domains. It became possible to get desirable services by conversation through the dialog system, but it is still necessary to improve separate modules, such as domain detection, intention detection, named entity recognition, and out-of-domain detection, in order to achieve stable service offer. When it misclassifies an in-domain sentence of conversation as out-of-domain, it will result in poor customer satisfaction and finally lost business. As there have been relatively small number of studies related to the out-of-domain detection, in this paper, we introduce a new method using a hierarchical Dirichlet process and demonstrate the effectiveness of it by experimental results on Korean dataset.

• The Journal of Engineering Research
• /
• v.2 no.1
• /
• pp.83-94
• /
• 1997

This paper documents how the user modeling shell BGP-MS is adapted to suit the user-modeling requirements of the Intelligent Dialog Model(IDM) and descriebes the background information about building a user model framework within BGP-MS, i.e. how to configure the shell system with application specific needs.

• Computational Structural Engineering
• /
• v.9 no.3
• /
• pp.97-105
• /
• 1996

An integrated environment for optimum design has been developed using Motif. The integrated environment is composed of the preprocessor, the postprocessor and the optimization part. The preprocessor is part of making a finite element model for optimum structural design and the postprocessor displays results of optimum design and the optimization part is the part which execute optimization. It is designed to reduce user's difficulties in structural optimum design. It used Graphic User Interface for the concurrent representation of various inputs and outputs through the dialog box, mouse and keyboard. Structural optimum design can be done easily through dialog box, menu, concurrent representation of modeling process and results of structural optimum design can be understood easily through stress contour, deformed model and graph of cost function.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.5 no.4
• /
• pp.331-335
• /
• 2004

In this paper, we modeling the oxidation, diffusion, and ion-implantation for semiconductor process simulation, and construct the integrated framework for efficient execution and continuous process simulation. For oxidation process, to predict the accurate LOCOS shape and stress distributions, stress-dependent viscous model was performed using SVP algorithm. For diffusion process, predeposition and OED simulation was performed using point defect theory. For ion implantation, Monte-Carlo method based on TRIM simulation was performed with various process conditions. For input to each unit process, we used the dialog boxes which are windows application's standards. This dialog box allows us to verify and minimize input error at input steps. Using the combination of compiler's function and windows's API function, simulation was done with small memory size.

• Annual Conference on Human and Language Technology
• /
• 2007.10a
• /
• pp.1-6
• /
• 2007

본 논문에서는 영어 회화 교육을 위한 예제 기반 대화 시스템에 대해 논한다. 기존의 획일적인 멀티미디어 영어 학습에서 벗어나 자연어 처리 및 대화 기술을 이용하여 지능적인 일대일 영어 회화 교육 제공을 목적으로 한다. 본 시스템은 미숙한 학습자 발화를 이해할 수 있으므로 불완전한 언어 구사 능력으로도 대화를 참여할 수 있는 체험형 학습을 제공한다. 이를 통해 학습자에게 영어를 배우려는 흥미로운 동기를 부여한다. 또한 학습자의 표현력 향상을 위한 교육적인 도움 기능을 갖추고 있다. 이를 위해 우리는 학습자의 미숙한 표현을 이해하는 통계 기반의 언어 이해 모듈, 도메인 확장성이 뛰어난 예제 기반 대화 관리 모듈, 교육 및 평가 기능을 개발하였다.

• Journal of the military operations research society of Korea
• /
• v.27 no.2
• /
• pp.134-148
• /
• 2001

In this paper, air-defense simulation model, called "DADSim", will be introduced. DADSim(Distributed Air Defense Simulation Model) was developed by Modeling&Simulation Lab of K.N.D.U.(Korea National Defence Univ) Weapon Systems Department. This model is an analysis-purpose model in the engagement-level. DADSim can simulate not only the global air-defense or Korean Peninsula but also the local air-defense or a battle field. DADSim uses the DTED(digital terrain elevation data) LeveII it for the representation of peninsula terrain characteristics. The weapon systems cooperated in the model are low/medium-range missile systems such as HAWK, NIKE, SAM. DADSim was designed in the way of object-oriented development method, implemented by C++ language. The simulation view is an event-sequenced object-orientation. For the convenience of input, output analysis, GUI(Graphic User Interface) of menu, window, dialog box, etc. are provided to the user, For the execution of DADSim, Silicon Graphic IRIX 6.3 or high version is required. DADSim can be used for the effectiveness analysis of­defence systems. Some illustrative examples will be shown in this paper.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.457-460
• /
• 2021

대화 시스템은 인공지능과 사람이 자연어로 의사 소통을 하는 시스템으로 크게 목적 지향 대화와 일상대화 시스템으로 연구되고 있다. 목적 지향 대화 시스템의 경우 날씨 확인, 호텔 및 항공권 예약, 일정 관리 등의 사용자가 생활에 필요한 도메인들로 이루어져 있으며 각 도메인 별로 목적에 따른 시나리오들이 존재한다. 이러한 대화는 사용자에게 명확한 발화을 제공할 수 있으나 자연스러움은 떨어진다. 일상 대화의 경우 다양한 도메인이 존재하며, 시나리오가 존재하지 않기 때문에 사용자에게 자연스러운 발화를 제공할 수 있다. 또한 일상 대화의 경우 검색 기반이나 생성 기반으로 시스템이 개발되고 있다. 검색 기반의 경우 발화 쌍에 대한 데이터베이스가 필요하지만, 생성 기반의 경우 이러한 데이터베이스가 없이 모델의 Language Modeling (LM)으로 부터 생성된 발화에 의존한다. 따라서 모델의 성능에 따라 발화의 품질이 달라진다. 최근에는 사전학습 모델이 자연어처리 작업에서 높은 성능을 보이고 있으며, 일상 대화 도메인에서도 역시 높은 성능을 보이고 있다. 일상 대화에서 가장 높은 성능을 보이고 있는 사전학습 모델은 Auto Regressive 기반 생성모델이고, 한국어에서는 대표적으로 KoGPT2가 존재한다. 그러나, KoGPT2의 경우 문어체 데이터만 학습되어 있기 때문에 대화체에서는 낮은 성능을 보이고 있다. 본 논문에서는 대화체에서 높은 성능을 보이는 한국어 기반 KoDialoGPT2를 개발하였고, 기존의 KoGPT2보다 높은 성능을 보였다.