• Annual Conference on Human and Language Technology
• /
• 1993.10a
• /
• pp.249-260
• /
• 1993

우리 일상 생활에서 매일 이루어지는 대화(conversation)를 살펴보면, 모든 대화는 어떤 '논제(topic)' 중심으로 이루어진다. 이 논문은 이런 논제 중심의 대화를 인지학적인 견해에서 재고해보고자 한다:논제는 우리의 인지구조로부터 어떻게 선택되며, 채택된 논제는 어떻게 상대방에게 전달되는가?

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.241-242
• /
• 2021

대화시스템에서 게임설명요청과 같은 주제대화의 경우, 입력문장의 의도를 정확하게 분류하는 것이 대화시스템 성능과 직결되므로 매우 중요하다. 본 논문에서는 개체명 인식 방법과 머신러닝 방법을 결합한 하이브리드 방법을 제안하여, 머신러닝 방법을 단독으로 사용하는 방법보다 주제대화의 의도 분류 성능을 향상시켰다.

• 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 the Korea Contents Association
• /
• v.17 no.1
• /
• pp.25-38
• /
• 2017

This study investigates non-native speakers(NNS) of English use of backchannels with beginner-intermediate learners' use of 'uh', 'um(uhm)', 'and' and 'hm' suggesting a view as a possible pedagogical implication. The initial aim of this study was to learn this phenomenon and observe their conversation patterns to compare with previous studies. Based on the previous findings, the analyzed data using conventional Conversation Analysis (CA) methods indicate the possible presence of L1 topic markers, '-un' and '-nun' in the form of L2 backchannel tokens when uttered by beginning and intermediate level speakers of English and the presences of L2 backchannel tokens appear only in front of noun phrases. Additionally, these same words with these tokens and when translated back to Korean also require topic markers of '-un' and '-nun.' Finally, This study discusses possible pedagogical implications with the initial analysis of backchannel tokens for Korean EFL learners. In addition, the ultimate goal of this study is to refine this analysis with follow up experiments to validate this investigation into a working hypothesis generating discussions of this backchannel phenomenon from being viewed as a hindrance to as an positive influence that needs to be understood.

• Science of Emotion and Sensibility
• /
• v.26 no.3
• /
• pp.115-128
• /
• 2023

This study examines the effects of a new app-based intervention program for conversational skills of children with high-functioning autism spectrum disorder (ASD). Participants in this study comprised 26 children diagnosed with autism, Asperger's syndrome, or pervasive developmental disorder-not otherwise specified (PDD-NOS). Participants were randomly assigned into a treatment group or a control group according to their ages, IQ, SCQ, and ASSQ scores. The treatment group met with teachers once a week for a single non-face-to-face class for nine weeks, along with conversation training at home using an app. The control group did not participate in any specific programs for conversational skills. Conversation data of all participants were collected before and after the intervention to compare the two groups based on changes in the conversational turn-taking and topic manipulation skills. When analyzed with respect to a Group X Period analysis of variance (ANOVA), the data indicated maintenance on the rate of appropriate listener's verbal responses in the treatment group, whereas the rate of inappropriate listener's verbal response significantly declined in the control group. In addition, the rate of conversation initiation and maintenance and the rate of appropriate initiation improved in the treatment group, whereas the rate of inappropriate initiation declined in this group. Overall, the study demonstrates promising effects of the novel App-based digital intervention on verbal conversational skills in children with high function ASD.

• Journal of KIISE:Software and Applications
• /
• v.33 no.10
• /
• pp.877-885
• /
• 2006

Recently it is proposed that the Bayesian networks used as conversational agent for topic inference is useful but the Bayesian networks require much time to model, and the Bayesian networks also have to be modified when the scripts, the database for conversation, are added or modified and this hinders the scalability of the agent. This paper presents a method to improve the scalability of the agent by constructing the Bayesian network from scripts automatically. The proposed method is to model the structure of Bayesian networks hierarchically and to utilize Noisy-OR gate to form the conditional probability distribution table (CPT). Experimental results with ten subjects confirm the usefulness of the proposed method.

• Journal of Satellite, Information and Communications
• /
• v.4 no.2
• /
• pp.1-4
• /
• 2009

This paper introduces not only what the ST-IT convergent technology is, but also the present technological status of ST and IT in order that the ST-IT convergent technology may not be a simple topic of conversation but a key word of our country's new growth engine. This paper also describes a development direction for the technology convergence as some dynamic changes can be anticipated to create the new value and market because the wall between technologies and industries may be broken down due to the development of STIT convergent technology in the future.

• Proceedings of the KSR Conference
• /
• 2011.10a
• /
• pp.2910-2916
• /
• 2011

Environmental conservation is becoming the major conversation topic in the 21st century, the era of environment. In the Law for the Preservation of Water Quality, article 53 states "A business unit which is doing business causing pollution caused by non-point pollutant or builds waste water discharge facilities, should report the installation of the non-point pollutant and install the required pollution control facilities". Environmental pollution caused by oil leaks during operation or maintenance has been found in the railway sector. Especially, rolling stock depot is most likely to be affected by environmental pollution. Therefore, in this paper We have investigated non-point pollutant in the rolling stock depot area and have studied adequate disposal method to minimize the effect of the non-point pollutant, hoping to supply the preliminary data for building an environment-friendly rolling stock depot.

• Proceedings of the Korean Institute of Interior Design Conference
• /
• 2003.05a
• /
• pp.82-87
• /
• 2003

Nowadays' culture' is an important topic of conversation and rigorous researches have been done about the cultures of our neighboring countries such as China and Japan. It is expected that studies concerning applications of each traditional culture in modern design will be made rigorously in the near future. In this context this study chose five-star hotel restaurants located in Korea and investigated how the Korean, Chinese and Japanese cultures are incorporated into their modern interior design. The data were classified by space and design elements. The results show that colorful Korean identity(or Koreanity) was applied in Korean restaurants rather than the simplicity and naturalness of traditional space. As for Chinese restaurants, a large scale of space which Chinese traditional space reveals was not adopted because of their location too, but brilliant patterns and colors were used consistently. The typical Japanese style of simple lines, colors and materials were reflected in Japanese restaurants.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.590-593
• /
• 2022

최근 코로나바이러스감염증-19(COVID-19)로 인해서 다양한 비대면 서비스가 증가하고 있는데 그 중에서 사람과 인공지능 간 의사소통하여 정보를 얻는 대화 시스템이 대표적인 서비스이다. 대화 시스템은 입력되는 단일 문장에 대한 정보만을 응답하기 때문에 이전 대화의 정보를 알기 위해서는 질문했던 내용을 다시 입력해야 하는 문제점이 있다. 이런 문제를 해결하고 대화 진행에 도움을 주기 위해서 본 논문에서는 대화 내 문장들의 다중 의도 탐지를 통한 공통 대화 주제 식별 시스템을 제안한다.