• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.3
• /
• pp.79-87
• /
• 2024

Recently, the importance of pre-trained language models (PLM) has been emphasized for natural language processing (NLP) such as text classification, sentiment analysis, and question answering. Korean PLM shows high performance in NLP in general-purpose domains, but is weak in domains such as finance, medicine, and law. The main goal of this study is to propose a language model learning process and method to build a financial-specific language model that shows good performance not only in the financial domain but also in general-purpose domains. The five steps of the financial-specific language model are (1) financial data collection and preprocessing, (2) selection of model architecture such as PLM or foundation model, (3) domain data learning and instruction tuning, (4) model verification and evaluation, and (5) model deployment and utilization. Through this, a method for constructing pre-learning data that takes advantage of the characteristics of the financial domain and an efficient LLM training method, adaptive learning and instruction tuning techniques, were presented.

• Korean Management Science Review
• /
• v.14 no.1
• /
• pp.87-105
• /
• 1997

There have been lots of research on temporal data management for the past two decades. Most of them are based on some logical data model, especially on the relational data model, although there are some conceptual data models which are independent of logical data models. Also, many properties or issues regarding temporal data models and temporal query languages have been studied. But some of them were shown to be incompatible, which means there could not be a complete temporal data model, satisfying all the desired properties at the same time. Many modeling issues discussed in the papers, do not have to be done so, if they take object-oriented data model as a base model. Therefore, this paper proposes a temporal data model, which is based on the object-oriented data model, mainly discussing the most essential issues that are common to many temporal data models. Our new temporal data model and query language will be illustrated with a small database, created by a set of sample transaction.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.14 no.1
• /
• pp.87-87
• /
• 1989

There have been lots of research on temporal data management for the past two decades. Most of them are based on some logical data model, especially on the relational data model, although there are some conceptual data models which are independent of logical data models. Also, many properties or issues regarding temporal data models and temporal query languages have been studied. But some of them were shown to be incompatible, which means there could not be a complete temporal data model, satisfying all the desired properties at the same time. Many modeling issues discussed in the papers, do not have to be done so, if they take object-oriented data model as a base model. Therefore, this paper proposes a temporal data model, which is based on the object-oriented data model, mainly discussing the most essential issues that are common to many temporal data models. Our new temporal data model and query language will be illustrated with a small database, created by a set of sample transaction.

• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.634-636
• /
• 1995

This paper presents a new distance relay modeling techniques which avoids unnecessary computational procedure. A general-purpose simulation language, called MODELS, has been added to the software ATP(Alternative Transients Program) providing a new option to perform numerical and logical manipulations of variables of an electrical system. This language has been designed to replace the previous option TACS (Transient Analysis of Control Systems) which permits to simulate a control system in conjunction with a large power network. One purpose of this study is to build a structure for modeling of digital distance relays within EMTP MODELS. Contrary to the traditional methods, the new method using MODELS reduce the number of simulation steps in modeling the distance relay.

• English Language & Literature Teaching
• /
• v.7 no.2
• /
• pp.55-75
• /
• 2002

The present study examined whether Kang's (1999) model of the relationships among language learning strategy use and language proficiency for the Asian students could be applied to a more heterogeneous group. In Kang's study, he collected information of language learning strategies of 957 foreign students learning English as a second language in American colleges through a questionnaire. He also measured the subjects' language proficiency with the Institutional Testing Program TOEFL (Test of English as a Foreign Language). This study analyzed the same data without the limitation of cultural identity. Structural equation modeling was used to model the relationships among strategy use and language proficiency. Then, the model of the present study was descriptively compared with Kang's (1999) model for the Asian students. The overall flow of the relationship paths appeared to vary very little across the two models, which would have indicated that the generalizability of Kang's (1999) model could be extended more than originally examined. (156)

• Journal of Distribution Science
• /
• v.16 no.11
• /
• pp.5-10
• /
• 2018

Purpose - The recent establishment of many varieties of English language in the globe has created many models of English such as world Englishes (WEs), English as a Lingua Franca (ELF), English as a family of languages, and English as an Intercultural Language (EIcL). Among the models, the present study highlights 'English as an intercultural language (EIcL)' in relation to distribution science business English teaching to elucidate what EIcL is and why it is critical and how it can be realized in the business English classrooms. Research design, data, and methodology - This study look into the EIcL paradigm that empowers all active users to view English as universal and at the same time enables them to develop critical skills to bridge intercultural gaps or to cross borders. Results - Rather than just focusing on an acquisition of standardized English(es), EIcL serves as a major contextual factor facilitating success in getting competence among the different English languages. Conclusions - EIcL is a promising and ultimately rewarding approach to the contemporary business English teaching arena. EIcL should be achieved through policies, textbooks or living abroad, and, above all, learners/teachers' active awareness and understanding' of the EIcL mainstreams.

• Smart Media Journal
• /
• v.13 no.6
• /
• pp.35-43
• /
• 2024

During the post-pandemic period, the interest in foreign language learning surged, leading to increased usage of language-learning apps. With the rising demand for these apps, analyzing app reviews becomes essential, as they provide valuable insights into user experiences and suggestions for improvement. This research focuses on extracting insights into users' opinions, sentiments, and overall satisfaction from reviews of HelloTalk, one of the most renowned language-learning apps. We employed topic modeling and emotion analysis approaches to analyze reviews collected from the Google Play Store. Several experiments were conducted to evaluate the performance of sentiment classification models with different settings. In addition, we identified dominant emotions and topics within the app reviews using feature importance analysis. The experimental results show that the Random Forest model with topics and emotions outperforms other approaches in accuracy, recall, and F1 score. The findings reveal that topics emphasizing language learning and community interactions, as well as the use of language learning tools and the learning experience, are prominent. Moreover, the emotions of 'admiration' and 'annoyance' emerge as significant factors across all models. This research highlights that incorporating emotion scores into the model and utilizing a broader range of emotion labels enhances model performance.

• Proceedings of the IEEK Conference
• /
• 2003.11b
• /
• pp.57-60
• /
• 2003

In order to overcome the limitation based on different avatar models, in this paper, we propose gesture communications between different avatar models using FBML (Facial Body Markup Language). The experimental results demonstrate a possibility that the proposed method could be used as an efficient means to overcome the problem.

• Journal of Digital Convergence
• /
• v.19 no.7
• /
• pp.199-208
• /
• 2021

Automatic Post Editing(APE) is the study that automatically correcting errors included in the machine translated sentences. The goal of APE task is to generate error correcting models that improve translation quality, regardless of the translation system. For training these models, source sentence, machine translation, and post edit, which is manually edited by human translator, are utilized. Especially in the recent APE research, multilingual pretrained language models are being adopted, prior to the training by APE data. This study deals with multilingual pretrained language models adopted to the latest APE researches, and the specific application method for each APE study. Furthermore, based on the current research trend, we propose future research directions utilizing translation model or mBART model.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.3
• /
• pp.451-461
• /
• 2024

Recently, various AI chatbots based on large language models have been released. Chatbots have the advantage of providing users with quick and easy information through interactive prompts, making them useful in various fields such as question answering, writing, and programming. However, a vulnerability in chatbots called "prompt injection attacks" has been proposed. This attack involves injecting instructions into the chatbot to violate predefined guidelines. Such attacks can be critical as they may lead to the leakage of confidential information within large language models or trigger other malicious activities. However, the vulnerability of Korean prompts has not been adequately validated. Therefore, in this paper, we aim to generate malicious Korean prompts and perform attacks on the popular chatbot to analyze their feasibility. To achieve this, we propose a system that automatically generates malicious Korean prompts by analyzing existing prompt injection attacks. Specifically, we focus on generating malicious prompts that induce harmful expressions from large language models and validate their effectiveness in practice.