• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.228-233
• /
• 2023

인간의 수동 평가 시 시간과 비용의 소모, 주석자 간의 의견 불일치, 평가 결과의 품질 등 불가피한 한계가 발생한다. 본 논문에서는 맥락을 고려하고 긴 문장 입출력이 가능한 ChatGPT를 활용한 한국어 요약문 평가가 인간 평가를 대체하거나 보조하는 것이 가능한가에 대해 살펴보았다. 이를 위해 ChatGPT가 생성한 요약문에 정량적 평가와 정성적 평가를 진행하였으며 정량적 지표로 BERTScore, 정성적 지표로는 일관성, 관련성, 문법성, 유창성을 사용하였다. 평가 결과 ChatGPT4의 경우 인간 수동 평가를 보조할 수 있는 가능성이 있음을 확인하였다. ChatGPT가 영어 기반으로 학습된 모델임을 고려하여 오류 발견 성능을 검증하고자 한국어 오류 요약문으로 추가 평가를 진행하였다. 그 결과 ChatGPT3.5와 ChatGPT4의 오류 요약 평가 성능은 불안정하여 인간을 보조하기에는 아직 어려움이 있음을 확인하였다.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.18 no.6
• /
• pp.191-199
• /
• 2023

The purpose of this study is to examine the impact of ChatGpt's quality on users' satisfaction and intention to continuous use it. For this purpose, a survey was conducted targeting college students in the Busan and Gyeongnam regions, and responses from a total of 155 people were verified using the SPSS 28.0 program. As a result of the study, reliability and stability among ChatGPT quality factors were found to have a positive effect on satisfaction with use and intention to continuous use. Satisfaction with the use of ChatGPT was found to have a positive effect on intention to continuous use.. Satisfaction with use was found to have a positive mediating effect between the reliability and stability of ChatGPT quality and intention to continous use it. As a result of this study, we aim to contribute to suggesting educational and policy directions necessary to promote the use of ChatGPT by presenting factors that affect users' intention to continuous use ChatGPT among the qualities of ChatGPT.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.5 no.2
• /
• pp.287-312
• /
• 2011

Internet chat programs and instant messaging services are becoming increasingly popular among Internet users. One of the crucial issues with Internet chat is how to manage the corresponding pairs of questions and answers in a sequence of conversations. Although many novel methodologies have been introduced to cope with this problem, most are poor in managing interruptions, organizing turn-taking, and conveying comprehension. The Internet environment is recently evolving into a 3D environment, but the problems with managing chat dialogues with the standard 2D text-based chat have remained. Therefore, we propose a more realistic communication model for chat agents in 3D virtual space in this paper. First, we propose a new method to measure the capacity of communication between chat agents and a novel visualization method to depict the hierarchical structure of chat dialogues. In addition, we are concerned with communication networks for virtual people (avatars) living in virtual worlds. In this paper we consider a microscopic aspect of a social network in a relatively short period of time. Our experiments show that our model is highly effective in a virtual chat environment, and the communication network based on our model greatly facilitates investigation of a very large and complicated communication network.

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2005.11a
• /
• pp.7-12
• /
• 2005

In this paper, we implemented an e-mail and chat program (client) for communication between mobile devices and PCs based on WIPI a South Korea's open wireless platform form developing device and content independent software to break from the way of developing contents that is dependent on different wireless platforms to each mobile communications company. While traditional e-mail and chat programs are written for PC-to-PC communication, we develop them for mobile-to-PC and mobile-to-mobile communications, and we expect to see various mobile contents in the future.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.47 no.6
• /
• pp.1038-1056
• /
• 2023

This study investigates the effects of ChatGPT's quality characteristics (service and information) on purchase intention and word of mouth intention. We distributed questionnaires among domestic men and women aged in their 20s and 30s who had experience of using ChatGPT. A total of 222 responses were subjected to frequency analysis, factor analysis, correlation analysis, and multiple linear regression analysis using the IBM SPSS statistical program version 26. The major findings were as follows: (1) The factors of service quality were categorized as Tangibility, Reliability, Empathy, and Assurance, while the factors of information quality were categorized as Recency, Accuracy, and Usefulness. (2) Among the service quality factors of ChatGPT, two factors (Reliability and Empathy) significantly impacted purchase intention, and three factors (Tangibility, Reliability, and Empathy) significantly affected word of mouth intention. (3) Among ChatGPT's information quality factors, two factors (Usefulness and Recency) had a significant effect on purchase intention, and two factors (Usefulness and Accuracy) exerted a significant influence on word of mouth intention. (4) Purchase intention had a significant effect on word of mouth intention.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.967-971
• /
• 2023

Recently, a variety of AI-based platform services are available, and one of them is ChatGPT that processes a large quantity of data in the natural language and generates an answer after self-learning. ChatGPT can perform various tasks including software programming in the IT sector. Particularly, it may help generate a simple program and correct errors using C Language, which is a major programming language. Accordingly, it is expected that ChatGPT is capable of effectively using Verilog HDL, which is a hardware language created in C Language. Verilog HDL synthesis, however, is to generate imperative sentences in a logical circuit form and thus it needs to be verified whether the products are executed properly. In this paper, we aim to select small-scale logical circuits for ease of experimentation and to verify the results of circuits generated by ChatGPT and human-designed circuits. As to experimental environments, Xilinx ISE 14.7 was used for module modeling, and the xc3s1000 FPGA chip was used for module embodiment. Comparative analysis was performed on the use area and processing time of FPGA to compare the performance of ChatGPT products and Verilog HDL products.

• Journal of KIISE
• /
• v.45 no.2
• /
• pp.134-140
• /
• 2018

A chat system is a computer program that understands user's miscellaneous utterances and generates appropriate responses. Sometimes a chat system needs to answer users' simple information-seeking questions. However, previous generative chat systems do not consider how to embed knowledge entities (i.e., subjects and objects in triple knowledge), essential elements for question-answering. The previous chat models have a disadvantage that they generate same responses although knowledge entities in users' utterances are changed. To alleviate this problem, we propose a knowledge entity embedding method for improving question-answering accuracies of a generative chat system. The proposed method uses a Siamese recurrent neural network for embedding knowledge entities and their synonyms. For experiments, we implemented a sequence-to-sequence model in which subjects and predicates are encoded and objects are decoded. The proposed embedding method showed 12.48% higher accuracies than the conventional embedding method based on a convolutional neural network.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.190-195
• /
• 2023

의사소통 기술에서 유머는 사람을 웃게 만들며 분위기를 환기시키고, 관계를 돈독하게 만드는 효과를 지닌다. 이를 자연어처리에서 유머 분류, 인식, 탐지로 적용하여 유머를 기계에 학습시키려 하는 다양한 시도가 진행되고 있지만 유머의 주관성과 윤리적 문제로 탁월한 성능을 기록하기 어렵고, 특히 한국어 유머에 대한 자연어처리 분야의 논의는 미비한 상태이다. 이에 본 연구는 유머 평가 체계를 만들어 ChatGPT에 적용하여 유머 인식의 주관성을 극복할 수 있는 자동화 실험을 진행한다. 이때, 유머의 윤리적 문제를 보완하기 위해 한국 법률을 적용한 윤리 기준을 도입하여 유머 데이터셋을 마련하였으며, 데이터셋을 ChatGPT에 fine-tuning 하여 재미있는 생성 모델의 개발 가능성을 실험하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.4
• /
• pp.209-216
• /
• 2023

In this paper, artificial intelligence agents ChatGPT and Stable Diffusion were used to explore the possibility of educational use by implementing a program to recommend picture materials for teaching and learning according to the class topic entered by teachers. The average time spent recommending all picture materials is about 6 minutes. In general, pictures related to keywords were recommended, and the letters in the recommended pictures could only know the intention to represent the letters, and the letters could not be recognized and the meaning could not be known. However, further research seems to be needed on the fact that the type or content of the recommended picture depends entirely on the response of ChatGPT and that it is not possible to accurately recommend the picture for all keywords. In addition, it was concluded that it is true that the recommended picture is related to the keyword, but the evaluation of whether it has educational value is the subject of discussion that should be left to the judgment of human teachers.

• Journal of Broadcast Engineering
• /
• v.24 no.4
• /
• pp.553-563
• /
• 2019

As the number of videos uploaded on live streaming platforms rapidly increases, the demand for providing highlight videos is increasing to promote viewer experiences. In this paper, we present novel methods for predicting highlights using chat logs and audio data in videos. The proposed models employ bi-directional LSTMs to understand the contextual flow of a video. We also propose to use the features over various time-intervals to understand the mid-to-long term flows. The proposed Our methods are demonstrated on e-Sports and baseball videos collected from personal broadcasting platforms such as Twitch and Kakao TV. The results show that the information from multiple time-intervals is useful in predicting video highlights.