• Annual Conference of KIPS
• /
• 2024.05a
• /
• pp.611-614
• /
• 2024

최근 많은 분야에서 인공지능을 사용한 산업이 각광을 받고 있고 그중 챗-GPT 로 인하여 챗봇에 관한 관심도가 높아져 관련 연구가 많이 진행되고 있다. 특히 질문에 대한 답변을 생성해주는 분야에 대한 연구가 많이 이루어지고 있는데, 질문-답변의 데이터 셋에 대한 학습 방식보다는 질문-답변-배경지식으로 이루어진 데이터 셋에 대한 학습 방식이 많이 연구가 되고 있다. 그러다 보니 배경지식을 어떤 방식으로 모델에게 이해를 해줄 지가 모델 성능에 큰 부분 차지한다. 그리고 최근 연구에 따르면 이러한 배경지식 정보를 이해시키기 위해 잠재 변수 모델링 기법을 활용하는 것이 높은 성능을 갖는다고 하고 트랜스포머 기반 모델 중 생성 문제에서 강점을 보이는 BART(Bidirectional Auto-Regressive Transformer)[1]도 주로 활용된다고 한다. 본 논문에서는 BART 모델에 잠재 변수 모델링 기법 중 잠재 변수를 어텐션에 곱하는 방식을 이용한 모델을 통해 답변 생성 문제에 관한 해결법을 제시하고 그에 대한 결과로 배경지식 정보를 담은 답변을 보인다. 생성된 답변에 대한 평가는 기존에 사용되는 BLEU 방식과 배경지식을 고려한 방식의 BLEU 로 평가한다.

• Informatization Policy
• /
• v.28 no.1
• /
• pp.3-21
• /
• 2021

Klaus Schwab's discussion on the Fourth Industrial Revolution provides a framework for predicting the direction of legal technology development. Technological convergence, which has emerged as the core concept of the Fourth Industrial Revolution has a significant effect on legal technology. In particular, various new technologies, such as legal chatbots and platforms, are being introduced to enhance efficiency and accessibility in the legal field. However, legal technology is still in its early stage, with institutional improvement needed to vitalize the industry. In this paper, we first specify the concept and classification of legal technology in Chapter 2, followed by trends and limitations in Chapter 3 and ways of vitalizing legal technology in the future in Chapter 4. To invigorate legal technology development, it is necessary to put in place legal regulatory measures that stipulate the active disclosure of legal data, such as precedents, and make free use of such measures. In the law, many issues, such as the safety of artificial intelligence, personal information protection, and ethical standards, will be discussed in the future. Therefore, via this paper, we hope to promote the formation of social consensus and prepare countermeasures, such as legislative measures.

• Journal of Sensor Science and Technology
• /
• v.30 no.6
• /
• pp.429-435
• /
• 2021

In this study, the creation of emotional dialogue was investigated within the process of developing a robot's natural language understanding and emotional dialogue processing. Unlike an English-based dataset, which is the mainstay of natural language processing, the Korean-based dataset has several shortcomings. Therefore, in a situation where the Korean language base is insufficient, the Korean dataset should be dealt with in detail, and in particular, the unique characteristics of the language should be considered. Hence, the first step is to base this study on a specific Korean dataset consisting of conversations on emotional topics. Subsequently, a model was built that learns to extract the continuous dialogue features from a pre-trained language model to generate sentences while maintaining the context of the dialogue. To validate the model, a chatbot system was implemented and meaningful results were obtained by collecting the external subjects and conducting experiments. As a result, the proposed model was influenced by the dataset in which the conversation topic was consultation, to facilitate free and emotional communication with users as if they were consulting with a chatbot. The results were analyzed to identify and explain the advantages and disadvantages of the current model. Finally, as a necessary element to reach the aforementioned ultimate research goal, a discussion is presented on the areas for future studies.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.71-79
• /
• 2024

ChatGPT, an interactive artificial intelligence (AI) chatbot developed by Open AI in the U.S., gaining popularity with great repercussions around the world. Some academia are concerned that ChatGPT can be used by students for plagiarism, but ChatGPT is also widely used in a positive direction, such as being used to write marketing phrases or website phrases. There is also an opinion that ChatGPT could be a new future for "search," and some analysts say that the focus should be on fostering rather than excessive regulation. This study analyzed consciousness about ChatGPT for college students through a survey of their perception of ChatGPT. And, plagiarism inspection systems were prepared to establish an education support model using ChatGPT and ChatGPT. Based on this, a university education support model using ChatGPT was constructed. The education model using ChatGPT established an education model based on text, digital, and art, and then composed of detailed strategies necessary for the era of the 4th industrial revolution below it. In addition, it was configured to guide students to use ChatGPT within the permitted range by using the ChatGPT detection function provided by the plagiarism inspection system, after the instructor of the class determined the allowable range of content generated by ChatGPT according to the learning goal. By linking and utilizing ChatGPT and the plagiarism inspection system in this way, it is expected to prevent situations in which ChatGPT's excellent ability is abused in education.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.4
• /
• pp.145-152
• /
• 2020

MRC (Machine reading comprehension) is the AI NLP task that predict the answer for user's query by understanding of the relevant document and which can be used in automated consult services such as chatbots. Recently, the BERT (Pre-training of Deep Bidirectional Transformers for Language Understanding) model, which shows high performance in various fields of natural language processing, have two phases. First phase is Pre-training the big data of each domain. And second phase is fine-tuning the model for solving each NLP tasks as a prediction. In this paper, we have made the Patent MRC dataset and shown that how to build the patent consultation training data for MRC task. And we propose the method to improve the performance of the MRC task using the Pre-trained Patent-BERT model by the patent consultation corpus and the language processing algorithm suitable for the machine learning of the patent counseling data. As a result of experiment, we show that the performance of the method proposed in this paper is improved to answer the patent counseling query.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.12
• /
• pp.1759-1768
• /
• 2022

This paper proposes a model to detect depression-related emotions in a user's speech using wellness dialogue scripts provided by AI Hub, topic-specific daily conversation datasets, and chatbot datasets published on Github. There are 18 emotions, including depression and lethargy, in depression-related emotions, and emotion classification tasks are performed using KoBERT and KOELECTRA models that show high performance in language models. For model-specific performance comparisons, we build diverse datasets and compare classification results while adjusting batch sizes and learning rates for models that perform well. Furthermore, a person performs a multi-classification task by selecting all labels whose output values are higher than a specific threshold as the correct answer, in order to reflect feeling multiple emotions at the same time. The model with the best performance derived through this process is called the Depression model, and the model is then used to classify depression-related emotions for user utterances.

• 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.

• Journal of the Korean earth science society
• /
• v.44 no.6
• /
• pp.675-692
• /
• 2023

This study used a Chatbot, a generative artificial intelligence (AI), to analyze the interaction between the Chatbot and students when exploring critical minerals from an epistemological aspect. The results, issues to be kept in mind in the teaching and learning process using AI were discussed in terms of the role of the teacher, the goals of education, and the characteristics of knowledge. For this study, we conducted a three-session science education program using a Chatbot for 19 high school students and analyzed the reports written by the students. As a result, in terms of form, the students' questions included search-type questions and non-search-type questions, and in terms of content, in addition to various questions asking about the characteristics of the target, there were also questions requiring a judgment by combining various data. In general, students had a questioning strategy that distinguished what they should aim for and what they should avoid. The Chatbot's answer had a certain form and consisted of three parts: an introduction, a body, and a conclusion. In particular, the conclusion included commentary or opinions with opinions on the content, and in this, value judgments and the nature of science were revealed. The interaction between the Chatbot and the student was clearly evident in the process in which the student organized questions in response to the Chatbot's answers. Depending on whether they were based on the answer, independent or derived questions appeared, and depending on the direction of comprehensiveness and specificity, superordinate, subordinate, or parallel questions appeared. Students also responded to the chatbot's answers with questions that included critical thinking skills. Based on these results, we discovered that there are inherent limitations between Chatbots and students, unlike general classes where teachers and students interact. In other words, there is 'limited interaction' and the teacher's role to complement this was discussed, and the goals of learning using AI and the characteristics of the knowledge they provide were also discussed.

• Information Systems Review
• /
• v.25 no.2
• /
• pp.125-144
• /
• 2023

Generative Artificial Intelligence (AI) technology is gaining global attention as it can automatically generate sentences, images, and voices that humans previously generated. In particular, ChatGPT, a representative generative AI service, shows proactivity and accuracy differentiated from existing chatbot services, and the number of users is rapidly increasing in a short period of time. Despite this growing interest in generative AI services, most preceding studies are still in their infancy. Therefore, this study utilized LDA topic modeling and keyword network diagrams to derive success factors for generative AI services and to propose successful business strategies based on them. In addition, using ChatGPT, a new research methodology that complements the existing text-mining method, was presented. This study overcomes the limitations of previous research that relied on qualitative methods and makes academic and practical contributions to the future development of generative AI services.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.3
• /
• pp.933-942
• /
• 2024

With the development of AI, Chat GPT, an artificial intelligence chatbot that appeared in 2022, is rapidly spreading to a wide range of people and expanding its usefulness. This study was conducted to examine college students' intention to continue using Chat GPT using a technology acceptance model. As a result of the study, all of Chat GPT's features had a positive effect on college students' perceived usefulness and perceived ease of use. However, among the features of Chat GPT, system quality and relative advantages did not directly affect the intention to continue using it. However, it was confirmed that it had an effect when perceived usefulness and perceived ease of use were mediated. The perceived usefulness and perceived ease of Chat GPT were verified to have a positive effect on the intention to continue using it.