• Journal of Information Technology Services
• /
• v.19 no.5
• /
• pp.83-91
• /
• 2020

Language Models such as BERT has been an important factor of deep learning-based natural language processing. Pre-training the transformer-based language models would be computationally expensive since they are consist of deep and broad architecture and layers using an attention mechanism and also require huge amount of data to train. Hence, it became mandatory to do fine-tuning large pre-trained language models which are trained by Google or some companies can afford the resources and cost. There are various techniques for fine tuning the language models and this paper examines three techniques, which are data augmentation, tuning the hyper paramters and partly re-constructing the neural networks. For data augmentation, we use no-answer augmentation and back-translation method. Also, some useful combinations of hyper parameters are observed by conducting a number of experiments. Finally, we have GRU, LSTM networks to boost our model performance with adding those networks to BERT pre-trained model. We do fine-tuning the pre-trained korean-based language model through the methods mentioned above and push the F1 score from baseline up to 89.66. Moreover, some failure attempts give us important lessons and tell us the further direction in a good way.

• Journal of Information Technology Applications and Management
• /
• v.16 no.2
• /
• pp.45-63
• /
• 2009

China has the largest number of the user of web 2.0 such as messengers and blogs, as of 2008 year. Chinese Internet digital market will grow from $85 billion in 2007 to $264 billion in 2015. The importance of Chinese Internet business is increasing, because of its size and growth potential. This research is focused on following two questions. First, what are the major characteristics of social networking services in China? In order to find out the answer about this question, the case study on Tencent QQ and Sina Poco, the most representative social networking services company in China, was done. And the reason of the use of social networking services, their contents, and the attitude toward the paid service were identified. Second, what are the major factors influencing the use of social networking services in China. User participation, network effect, usefulness, and system quality were inferred as the factors influencing the use. These factors were based on motivation theory, technology acceptance model, and the related research papers. This research model was proved by data analysis using Partial Least Square. As results, the use of social networking services was influenced by usefulness, network effect, user participation, and system quality. But social influence was not significant of the use of social networking services.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.32 no.2
• /
• pp.101-123
• /
• 2021

This study analyses the questions and answers contained in the Knowledge Information Database of the collaborative digital reference service, 'Ask a librarian'. And based on the results of status of user requests, this study draws information usage behavior in the early stages of the service was derived. 1,124 Knowledge Information Database items out of 3,506 cases was analyzed by nine criterion. ① Number of questions and whether to be reference questions, ② Subject and keywords of the question, ③ Purpose of the question, ④ Type of question, ⑤ User's information request, ⑥ Information source and reference services provided by the librarian, ⑦ Number of days to answer, ⑧ Level of the participating library, ⑨ Question type by topic. As a results of analysis, first, users asked for reference questions from various topics as needed, rather than one from a similar topic at a time, but more than half of the total pure reference questions were from the field of library information science. Second, about 71.35% of users were using the 'Ask a librarian' service to recommend a list of information resources related to a particular topic or research problem, and there were also questions that required consultation on the reading situation. Third, the most preferred sources of information for users were bibliography, and in the case of online information sources, users did not relatively prefer them. Fourth, the number of days required to answer was able to confirm significant differences depending on the type of question and the level of the participating library. Fifth, 31.33% of the purpose of the general field question showed that were self-generated.

• Journal of Korean Library and Information Science Society
• /
• v.40 no.1
• /
• pp.133-155
• /
• 2009

To deal with a new environment of information technologies in the 21 Century, many libraries around the world have made great efforts to develop online knowledge-information services. In Korea, the National Library initiated an online knowledge-information services, in 2008. Through case studies and practical tests of online knowledge-information services, this article discusses plans for developing . The article explores definitions and types of online knowledge-information services, and analyzes online knowledge-information services in Denmark, Sweden, Finland, and Korea. Futhermore, practical reviews on the four services are conducted through 'question-answer' tests. As a result, the article discusses present and future tasks for improving .

• The Journal of the Korea Contents Association
• /
• v.20 no.10
• /
• pp.25-34
• /
• 2020

Community question and answering service is one of the main sources of information and knowledge in the Web. The quality of information in question and answer documents is determined by the clarity of the question and the relevance of the answers, and the readability of a document is a key factor for evaluating the quality. This study is to measure the quality of documents used in community question and answering service. For this purpose, we compare the frequency of occurrence by vocabulary level used in community documents and measure the readability index of documents by institution of author. To measure the readability index, we used the Dale-Chall formula which is calculated by vocabulary level and sentence length. The results show that the vocabulary used in the answers is more difficult than in the questions and the sentence length is longer. The gap in readability between questions and answers is also found by writing institution. The results of this study can be used as basic data for improving online counseling services.

• Journal of Korean Library and Information Science Society
• /
• v.41 no.4
• /
• pp.127-150
• /
• 2010

This study aims to analyze the gap between university students' cognitions and expectations on users' cognitions about dimensions of library staff service quality and the reason of gap. The results showed that the overal service didn't reach the users' minimum expectation. Among the every item of service quality, the greatest expectation service was the quick delivery of non home library materials and staff's politeness. The most great was in-depth subject services and friendly encounter. The staff service quality gave the library satisfaction; in-depth subject services, exact understanding of user needs and politeness. The great gaps were caused to the lack of willingness to answer question, the lack of communication, and the lack of user care etc.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.5
• /
• pp.1313-1327
• /
• 2013

How to make people keep both the confidentiality of the sensitive data and the privacy of their real identity in communication networks has been a hot topic in recent years. Researchers proposed privacy-preserving authenticated key exchange protocols (PPAKE) to answer this question. However, lots of PPAKE protocols need users to remember long secrets which are inconvenient for them. In this paper we propose a lightweight three-party privacy-preserving authentication key exchange (3PPAKE) protocol using smart card to address the problem. The advantages of the new 3PPAKE protocol are: 1. The only secrets that the users need to remember in the authentication are their short passwords; 2. Both of the users can negotiate a common key and keep their identity privacy, i.e., providing anonymity for both users in the communication; 3. It enjoys better performance in terms of computation cost and security. The security of the scheme is given in the random oracle model. To the best of our knowledge, the new protocol is the first provably secure authentication protocol which provides anonymity for both users in the three-party setting.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.4
• /
• pp.369-381
• /
• 2021

Artificial Intelligence(AI) technology can be used in arts exhibitions ranging from planning exhibitions, filed progress, and evaluation. AI has been expanded its scope from planning exhibition and guidance services to tools for creating arts. This paper focuses on chatbots that utilize exhibition and AI technology convergence to provide information and services. To study more specifically, I developed a chatbot for exhibition services using the Naver Clova chatbot tool and information from the National Museum of Modern and Contemporary Art(MMCA), Korea. In this study, information was limited to viewing and exhibition rather than all information of the MMCA, and the chatbot was developed which provides a scenario type to get an answering user want to gain through a button and a text question and answer(Q&A) type to directly input a question. As a result of evaluating the chatbot with six items according to ELIZA's chatbot evaluation scale, a score of 4.2 out of 5 was derived by completing the development of a chatbot to be used to deliver viewing and exhibition information. The future research task is to create a perfect chatbot model that can be used in an actual arts exhibition space by connecting the developed chatbot with continuous scenario answers, resolving text Q&A-type answer failures and errors, and expanding additional services.

• Journal of Korean society of Dental Hygiene
• /
• v.21 no.4
• /
• pp.403-412
• /
• 2021

Objectives: The objectives of this study were to assess oral health knowledge and behavior levels of community pharmacists as a step toward projecting them to play the role of oral health partners and to confirm pharmacists' willingness to participate in oral health education programs. Methods: t-test and one-way analysis of variance were performed to analyze the data, and correlation analysis was also performed. Results: The mean score for pharmacists' oral health knowledge was 7.29 out of 10. Of the 12 questions asked, the correct answer rate was highest for the question about the effect of smoking cessation on periodontal disease prevention; conversely, the correct answer rate was lowest for the question about the effect of taking medication for gingival infections on periodontal disease prevention. The mean score for pharmacists' oral health behavior was 2.97 out of 4 points. Of all oral health behaviors, brushing twice a day was the most practiced, whereas immediately visiting a dentist in case of an oral health issue was the least practiced. Pharmacists' oral health knowledge and behavior levels showed a weak positive correlation with their intention to participate in oral health education programs. Conclusions: Oral health education programs are necessary to improve community pharmacists' oral health knowledge and behavior.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.7
• /
• pp.249-254
• /
• 2019

The concept of 'Edu-Tech', which is rapidly reorganized around e-Learning, has been spreading along with the development of intelligent information technology according to the fourth industrial revolution such as Artificial Intelligence (AI), Internet of Things (IoT), BigData. Currently, leading companies are conducting online education services, but real-time two-way communication is difficult. In addition, in the case of off-line class, there are many students, and not only the time is limited, but also they often miss the opportunities to ask questions. In order to solve these problems, this paper develops a real - time interactive question and answer management system that can freely questions both on - line and off - line by combining the benefits of offline instant answers and the advantages of online openness. The developed system is a real-time personalized education system that enables the respondent to check the situation of the questioner in real time and provide a customized answer according to the inquirer's request. In addition, by measuring and managing the system usage time in seconds, the questioner and the respondent can efficiently utilize the system.