• Journal of the Korea Society of Computer and Information
• /
• v.29 no.10
• /
• pp.77-87
• /
• 2024

With the recent advancements in artificial intelligence, various chatbots have emerged, efficiently performing everyday tasks such as hotel bookings, news updates, and legal consultations. Particularly, generative chatbots like ChatGPT are expanding their applicability by generating original content in fields such as education, research, and the arts. However, the training of these AI chatbots requires large volumes of conversational text data, such as customer service records, which has led to privacy infringement cases domestically and internationally due to the use of unrefined data. This study proposes a methodology to quantitatively assess the re-identification risk of personal information contained in conversational text data used for training AI chatbots. To validate the proposed methodology, we conducted a case study using synthetic conversational data and carried out a survey with 220 external experts, confirming the significance of the proposed approach.

• Journal of Korean Philosophical Society
• /
• v.129
• /
• pp.267-290
• /
• 2014

The slippery slope argument means that if we accept a type of action A, we are committed to accepting B, C and eventually N. Then, N is situation which we must not accept morally. It works causal mechnism that B because A is raised, C because B is raised. But in the logic textbooks and treatises, the slippery slope argument is classified as fallacy. The reason is that the argument is not a causal argument. Actually, it is a probable. Also it is argued that the argument is wrong because it fears about the future extremely. But We can not say all slippery slope argument is fallacy even though a slippery slope argument is sometimes fallacy. I think it is persuasive argument in a significant place. Therefore I argue that the argument is not simple logic as a form of thinking, but practical reasoning applied the context of dialogue. So in order to find it to be practical reasoning we demand the new understanding to fallacy theory. In traditionally, fallacy is defined to wrong reasoning logically, but according to Walton, fallacy means a verbal tactic or deceptive trick that can be used to cause someone to fall down in argument. That is to say, whether or not the argument is successful depends on how it uses as argument tactic in a given context of dialogue. Therefore I argue that whether or not the argument is successful, because of it is practical problem used in a context of dialogue, is to be approached to pragma and dialectical method, not semantic.

• 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.

• Journal of the Daesoon Academy of Sciences
• /
• v.43
• /
• pp.139-177
• /
• 2022

The only text that aids in the understanding of Songs of the Dao of Great Gods (大化神道歌詞), which was established by Yun Jin in 1984, is Mok-wun daegyeong (木運大經, The Great Scripture of Wood-Destiny) published by Oh Yeol-gyun in 1976. This scripture includes five songs: Wun-hoe dongbang-ga (運回東方歌, Songs of Destiny-Returning to the East), Gung-eul-ga (弓乙歌, Songs of Gung-eul), Dodeok-sa (道德詞, Morality Poems), Palguae-gugung byeon-yeok-ga (八卦九宮變易歌, Songs on the Changes of the Eight Trigrams and Nine Palaces), and Nakdang-ga (樂堂歌, Songs of the Paradisiacal Lands). Songs of the Dao of Great Gods, which is prone to embracing Daoist characteristics, is meant to be sung upon the realization of the Later World, the ideal earth. This is expressed as spring. In addition, we can easily find key terms such as Sampung-ga (三豊歌), Yangbaek-segye (兩白世界), Gung-eul-ga (弓乙歌), Gunggung-euleul (弓弓乙乙), Yanggung (兩弓), Euleul (乙乙), Gung-eul seonin (弓乙仙人), Samin-ilseok (三人一夕), Yijae-jeonjeon (利在田田), Gung-eul jiri (弓乙之理), Naenggeum-bugeum (冷金浮金), Seokjeong-gon (石井昆), Yangbaek (兩白), Sampung (三豊), and Sodumujok (小頭無足), all of which appear frequently in traditional prophecies and the faiths they have inspired. The precise meaning of these terms has yet to be revealed. Furthermore, Songs of the Dao of Great Gods contains lyrics prophesying that the return of the wood-destiny of the East and emphasizing the destiny of 3-8 wood as based on the Yellow River Chart (河圖). Songs of the Dao of Great Gods, originated the term, the World of Paradisiacal Lands (樂堂世界), and prophesyed that the wood-destiny of the East would return to create a new world that took Korea as its center. The text emphasized wood-destiny, symbolized by spring, and argued that the Dao of Great Gods could be ascetained from the principle of water-producing wood (水生木) found in the Eastern study of changes (易學) as approached by Choi Su-Wun (水雲), the founder of Donghak (東學).

• 건강소식
• /
• v.37 no.10
• /
• pp.30-31
• /
• 2013

마주한 상대와 재미있게 대화를 이어가다가도 은근 눈치를 보며 입을 가리게 하는 증상 입 냄새. 그렇다면 입 냄새는 왜 나는 것일까? 본인뿐만 아니라 대화 상대에게 불쾌감을 줄 수 있고, 심한 경우 입 냄새가 날지도 모른다는 생각에 사람들을 기피하게 하는 입 냄새의 원인과 해결 방법을 알아보자.

• Journal of the Korean Society for Railway
• /
• v.5 no.3
• /
• pp.15-21
• /
• 2002

옆의 사진을 보고 무엇을 느낄 수 있나\ulcorner 시속 30~40km/h의 열차가 레일이음매에서 발생하는 충격음을 내며 지나가고 있다. 여행 중 및 사람과 정다운 대화를 하면서 여행 그 자체를 즐기고 있다. 때로는 차장과 대화를 하면서 기관사를 신뢰하고, 안전하다는 믿음으로 여행을 한다. 가끔은 큰소리로 기적을 울려지지만 소음이라기 보다는 오히려 열차다운 면이기에 더욱 정이 간다. 느리다고 불평하는 사람도 없고, 궤도틀림으로 인한 진동이 심하다고 나무라는 사람도 없다. (중략)

• The Science & Technology
• /
• v.31 no.4 s.347
• /
• pp.75-80
• /
• 1998

기계가 말하고 알아듣는 시대가 빠른 걸음으로 다가오고 있다. 21세기 초에는 외국어를 모르는 사람들도 외국인과 대화할 때 거추장스럽게 통역관을 내세우지 않아도 된다. 통역용 소프트웨어가 내장된 전화기가 등장하는가 하면 포켓용 통역장치가 그때그때 대화내용을 우리말과 외국어로 옮겨 합성소리로 알려준다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2000.10a
• /
• pp.388-399
• /
• 2000

본 논문은 정수계획 문제로 수리모형화 되는 선박운항 일정계획 문제에 대한 컴퓨터 그래픽 기반의 상호 대화식 모델링 시스템의 개발에 관해서 논한다. 선박운항 일정계획 문제는

• Broadcasting and Media Magazine
• /
• v.4 no.1
• /
• pp.43-53
• /
• 1999

Data Broadcast는 디지털TV에 PC가 가질 수 있는 멀티미디어 대화형 서비스 기술을 부여한 것으로 Interactive 디지털TV라고 할 수 있다. 대화형 서비스를 제공하기 위한 컨텐츠, 방송, 통신, 단말에 이르는 시스템에 대한 기술 규격을 정의하고 실제로 이를 구현하여 시험하는 것을 목적으로 하고 있다. 이 문서에서는 미국 규격을 중심으로 Data Broadcast Service관련 기술의 동향을 기술한다.

• The Science & Technology
• /
• v.32 no.9 s.364
• /
• pp.22-23
• /
• 1999

과학과 종교는 대화가 가능한가? 지난 4월 미국에서는 노벨물리학 수상자인 와인버그와 성공회 목사인 폴킹혼이 '과학과 종교간의 건설적인 대화'라는 제목으로 토론을 벌였다. 이들 두사람은 신의 존재와 사람의 선악행위 등을 토론대상으로 올려 놓았지만 신학의 권위는 계시에 있고 과학의 권위는 실험에 있기 때문에 중요한 형이상학적인 문제는 해결되지 않은 채 토론은 끝났다.