• 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.

• Proceedings of the KIEE Conference
• /
• 1998.07g
• /
• pp.2405-2407
• /
• 1998

Implementation of a process control language for a pager manufacturing is dealt in this paper. The pager manufacturing process is consisted of a tune and an exam part. In the tune part, three capacitor trimmers are tuned to optimize the state of the pager. In the exam part, message receiving status with the arbitrary calling is tested using a vision system. The program has the ability to reuse the address discarded in the exam part when the, pager testing is not working properly even though there exist the processing gaps between two processes. The system is composed of a personal computer(PC586) and TEM-cells, Flex pager testers, an oscilloscope, a camera, and actuators. Visual Basic running on the Windows 95 is used to implement the control software which has the GUI to make an operator convenient. The validity of applying the completed program to practical machines, which are developing in the KITECH, is shown by using the virtual machine.

• English Language & Literature Teaching
• /
• v.11 no.2
• /
• pp.149-170
• /
• 2005

The purpose of this paper is to make a sentence systemic within the category of structural grammar for the modality in which a speaker expresses his attitude. It is the priority of a language to communicate meaning. By eliminating the theoretical description of traditional grammar, this paper also aims to illustrate the concepts of nine modal verbs through a systemic network. The concept of modality includes both the epistemic and the deontic characteristics of modality. Epistemic modality is associated with either knowledge or belief on the part of a speaker who gives his own judgments about the state of affairs, events, or actions. However, deontic modality is related to either the possibility or the necessity of acts that a speaker performs to give permission or fulfill an obligation. In conclusion, all the subsystems are described within the framework of the systemic network, with the intention of including all the potential options of the semantic functions available in a situation.

• Proceedings of the Korea Society for Simulation Conference
• /
• 1992.10a
• /
• pp.12-12
• /
• 1992

This paper proposes an analysis method of Petri nets (PNs) using the relational algebra (RA). More specifically, we represent PNs in relations of the relational model. Based on such representation, we first develop an algorithms for analyzing properties of PNs, such as boundedness, conservation, coverability, reachability, and liveness. The advantage of this approach is as follows: First, the algorithms represented by RA can be easily converted to a query language such as SQL of the widely used, commercial relational database management systems (DBMSs). Second, we can alleviate the problem of state space explosion because relational DBMSs can handle large amounts of data efficiency. Finally, we can use the DBMS's query language to interpret the Petri nets and make simulation.

• Journal of the Korea Society for Simulation
• /
• v.1 no.1
• /
• pp.37-47
• /
• 1992

This paper proposes an analysis method of petri nets(PNs) using the relational algebra(RA). More wpecifically, we represent PNs in relations of the relational model. Based on such representation, we first develop an algorithm for generating reachability trees of PNs. we then develop an algorithm for generating reachability trees of PNs. We then develop algorithms for analyzing properties of PNs, such as boundedness, conservation, coverability, reachability, and liveness. The advantage of this approach is as follows: First, the algorithms represented by RA can be easity converted to a query language such as SQL of the widely used, commerical relational database management systems(DBMSs). Second, we can alleviate the problem of state space explosion because relational DBMSs can handle large amounts of data efficiently. Finally, we can use the DBMS's query language to interpret the Petri nets and make simulation.

• International Journal of Computer Science & Network Security
• /
• v.21 no.11
• /
• pp.328-332
• /
• 2021

The article considers general tendencies in world and education, and also both principles and methods of forming professional, communicative, intercultural competences and in the process of teaching foreign language for professional purposes in the conditions of engineering, economic and other non-linguistic specialties at technical university. The article views some essential issues of this competence including awareness of pedagogical values, the construction of the pedagogical process, pedagogical communication and behavior; pedagogical technology, its essence, structural components, understanding of innovative components of professional activity, requirements for the design and engineering of pedagogical technologies.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.388-391
• /
• 2019

과편향 뉴스 판별(hyperpartisan news detection)은 뉴스 기사가 특정 인물 또는 정당에 편향되었는지 판단하는 task이다. 이를 위해 feature-based ELMo + CNN 모델이 제안되었으나, 이는 문서 임베딩이 아닌 단어 임베딩의 평균을 사용한다는 한계가 존재한다. 따라서 본 논문에서는 feature-based 접근법을 따르며 Sentence-BERT(SentBERT)의 문서 임베딩을 이용한 feature-based SentBERT 기반의 과편향 뉴스 판별 모델을 제안한다. 제안 모델의 효과를 입증하기 위해 ELMO, BERT, SBERT와 CNN, BiLSTM을 적용한 비교 실험을 진행하였고, 기존 state-of-the-art 모델보다 f1-score 기준 1.3%p 높은 성능을 보였다.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.505-506
• /
• 2021

최근 인터넷에서 기하급수적으로 증가하는 방대한 양의 텍스트를 자동으로 요약하려는 연구가 활발하게 이루어지고 있다. 자동 텍스트 요약 작업은 다양한 사전학습 모델의 등장으로 인해 많은 발전을 이루었다. 특히 T5(Text-to-Text Transfer Transformer) 기반의 모델은 자동 텍스트 요약 작업에서 매우 우수한 성능을 보이며, 해당 분야의 SOTA(State of the Art)를 달성하고 있다. 본 논문에서는 방대한 양의 한국어를 학습시킨 사전학습 모델 KE-T5를 활용하여 자동 논문 요약을 수행하고 평가한다.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.518-523
• /
• 2020

본 논문에서는 목적 지향 대화 시스템을 위한 대화 상태 추적 시스템과 사용자 시뮬레이터를 설계 및 제안한다. 사용자 시뮬레이터는 작성된 대화 상태 추적 시스템을 평가하기 위한 용도로 사용된다. 본 논문에서 제안하는 대화 상태 추적 시스템은 대화 기록과 함께 사전에 학습된 대화 기록 및 규칙/통계 기반 추론 시스템의 추론 결과를 입력으로 받는다. 그리고 입력된 발화 기록 중 마지막 사용자 발화의 사용자 목표와 개체명 그리고 다음 시스템 발화의 화행을 추론한다. 또한, 작성된 대화 상태 추적기의 성능을 평가하고 분석하기 위해, 주어진 환경에서 시스템과 대화를 수행하며 대화 시스템의 성능을 평가하는 사용자 시뮬레이터를 구현 및 적용하였다. 본 연구에서 수행된 실험과 분석을 통해, 규칙 및 통계 기반의 기반 시스템을 이용해 목표 시스템의 성능 개선이 가능함을 보인다. 또한, 제안하는 사용자 시뮬레이터는 규칙과 통계를 이용해 평가 코퍼스 없이 여러 상황에 대해 대화 시스템의 성능을 평가할 수 있다.

• Journal of Digital Contents Society
• /
• v.14 no.2
• /
• pp.143-149
• /
• 2013

Many researchers and developers take a greater interest on the LOD AI techniques as users demand more elaborate and sophisticated game AI in recent years. However, contrary to the traditional geometry LOD, existing LOD AI techniques can be used only to a limited extent. Therefore, in this paper, I propose an LOD AI technique, which uses HSM(Hierarchical State Machine) and the Lua script language as the method to control game objects. Using the proposed approach, we can easily produce multilevel AI models for LOD and design various objects without hard-coding state machines. Moreover, in order to show the effectiveness of the presented technique, this paper exemplifies the results of the efficiency test through the prototype engine.