• The Transactions of the Korea Information Processing Society
• /
• v.13 no.4
• /
• pp.181-188
• /
• 2024

Traditional profanity detection methods have limitations in identifying intentionally altered profanities. This paper introduces a new method based on Named Entity Recognition, a subfield of Natural Language Processing. We developed a profanity detection technique using sequence labeling, for which we constructed a dataset by labeling some profanities in Korean malicious comments and conducted experiments. Additionally, to enhance the model's performance, we augmented the dataset by labeling parts of a Korean hate speech dataset using one of the large language models, ChatGPT, and conducted training. During this process, we confirmed that filtering the dataset created by the large language model by humans alone could improve performance. This suggests that human oversight is still necessary in the dataset augmentation process.

• Journal of the International Relations & Interdisciplinary Education
• /
• v.2 no.1
• /
• pp.43-55
• /
• 2022

Through literary research, this study aims to study chinese characters in the Chosun Dynasty from the perspective of international exchange. While sorting out the historical materials, it investigates the implementation organ, educational content and main characteristics of Chinese education in the Chosun Dynasty, its influence on the Korean peninsula at that time and Its enlightenment to today's Chinese international education. The results show that the Chinese language education institutions in the Chosun Dynasty mainly played the role of Chinese language education in the Si service academy and the Sheng Wen Academy. The contents of Chinese language education mainly include the development of oral Chinese teaching materials, the publication of rhymes and other reference books, the compilation of dictionaries and the training of Chinese translators. Through the in-depth study of Chinese rhymes, the Korean Peninsula created its own Korean national character in 1443, getting rid of the will of Chinese characters. The invention of Korean language has greatly encouraged the political, economic and cultural development of the Korean peninsula. In addition, the Chinese language education in the Chosun Dynasty provides a good experience for today's Chinese international education in China.

• International Journal of Computer Science & Network Security
• /
• v.24 no.2
• /
• pp.101-112
• /
• 2024

Telugu language is considered as fourth most used language in India especially in the regions of Andhra Pradesh, Telangana, Karnataka etc. In international recognized countries also, Telugu is widely growing spoken language. This language comprises of different dependent and independent vowels, consonants and digits. In this aspect, the enhancement of Telugu Handwritten Character Recognition (HCR) has not been propagated. HCR is a neural network technique of converting a documented image to edited text one which can be used for many other applications. This reduces time and effort without starting over from the beginning every time. In this work, a Unicode based Handwritten Character Recognition(U-HCR) is developed for translating the handwritten Telugu characters into English language. With the use of Centre of Gravity (CG) in our model we can easily divide a compound character into individual character with the help of Unicode values. For training this model, we have used both online and offline Telugu character datasets. To extract the features in the scanned image we used convolutional neural network along with Machine Learning classifiers like Random Forest and Support Vector Machine. Stochastic Gradient Descent (SGD), Root Mean Square Propagation (RMS-P) and Adaptative Moment Estimation (ADAM)optimizers are used in this work to enhance the performance of U-HCR and to reduce the loss function value. This loss value reduction can be possible with optimizers by using CNN. In both online and offline datasets, proposed model showed promising results by maintaining the accuracies with 90.28% for SGD, 96.97% for RMS-P and 93.57% for ADAM respectively.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.2
• /
• pp.43-50
• /
• 2024

This paper evaluates the Korean sentiment analysis performance of large language models like GPT-3.5 and GPT-4 using a zero-shot approach facilitated by the ChatGPT API, comparing them to pre-trained Korean models such as KoBERT. Through experiments utilizing various Korean sentiment analysis datasets in fields like movies, gaming, and shopping, the efficiency of these models is validated. The results reveal that the LMKor-ELECTRA model displayed the highest performance based on F1-score, while GPT-4 particularly achieved high accuracy and F1-scores in movie and shopping datasets. This indicates that large language models can perform effectively in Korean sentiment analysis without prior training on specific datasets, suggesting their potential in zero-shot learning. However, relatively lower performance in some datasets highlights the limitations of the zero-shot based methodology. This study explores the feasibility of using large language models for Korean sentiment analysis, providing significant implications for future research in this area.

• 재활복지
• /
• v.17 no.4
• /
• pp.371-382
• /
• 2013

Recently, the number of those who were transplanted cochlear implants increased as health insurance increases has expanded. Last six years between 2005 to 2009, patients who received a cochlear implant surgery were about 3,300 and number of cochlear implants in adults of them have shown growing aspects. In the case of young children, they actively participated auditory training program after cochlear implant surgery and the studies related to auditory training in child are many, but the studies related to auditory training in adults is insufficient. In this study, we perform the auditory training for the female adult (age 54) received cochlear implant after language acquisition used Ling 6 sounds test, standardized consonants, vowels and sentences listening test and word recognition and confirmation test. As a result after auditory training for 10 weeks, she identified all phonemes in Ling 6 sound test and performed close to 100% in standardized consonants, vowels and sentences listening tests. Also, she improved the ability of real-world environmental sound and real-world words identifications by 57-95%. The results of this study showed the need of auditory training program with systematic and effective planning and considering the characteristics of the individual for adults.

• Journal of Korea Society of Industrial Information Systems
• /
• v.12 no.2
• /
• pp.49-59
• /
• 2007

This paper is about an system which can perform automatic semantic annotation to actualize "Semantic Web." Since it is impossible to tag numerous documents manually in the web, it is necessary to gather large Korean web documents as training data, and extract features by using natural language techniques and a thesaurus. After doing these, we constructed concept classifiers through the SVM (support vector machine) teaming algorithm. According to the characteristics of Korean language, morphological analysis and syntax analysis were used in this system to extract feature information. Based on these analyses, the concept code is mapped with Kadokawa thesaurus, which made it possible to map similar words and phrase to one concept code, to make training vectors. This contributed to rise the recall of our system. Results of the experiment show the system has a some possibility of semantic annotation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.507-509
• /
• 2013

This paper covers the individual with mild autistic disorder complementary and alternative communication Support program by using Android. The complementary and alternative communication is the communicative system to help handicapped people who have problems with colloquial and non-colloquial communication. In this research, we will introduce the communication manner of autistic disorder, the method of how to measure the language disabled people's selection and frequency of the words, and the basic training method of Autism people's communication ways. In this paper, we developed complementary and alternative communication system which used language representative method to encourage language disabled people to study on communication in effective way. We utilized 'TTS technology' to enable handicapped people delivering their mind with the voice; moreover, by listening their voice by themselves, we accelerated their studies on communications. In addition, by offering 'Painting function', we promoted handicapped people to deliver their purpose widely and efficiently. Also, we built the smart system in 'Painting function' to collect frequency and educated degree data from the users by using this function, we can analyze the percentage of conscious and unconscious communication way of Autism cases to help them.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.10
• /
• pp.97-107
• /
• 2013

The latest programming paradigm has been mostly geared toward object-oriented programming and visual programming based on the object-oriented programming. However, object-oriented programming has a more difficult and complicated concept compared with that of existing structural programming technique; thus it has been very difficult to educate students in the IT-related department. This study designed and implemented a Java robot training kit in which the Java virtual machine is built so that it may enhance the desire and motivation of students for learning the object-oriented programming using the training kit which is possible to attach various input and output devices and to control a robot. The developed Java robot training kit is able to communicate with a computer through the USB interface, and it also enables learners to manufacture a robot for education and to practice applied programming because there is a general purpose input and output port inside the kit, through which diverse input and output devices, DC motor, and servo motor can be operated. Accordingly, facing the IT fusion era, the wall between the academic circles and the major becomes lower and the need for introducing education about creative engineering object-oriented programming language is emerging. At this point, the Java robot training kit developed in this study is expected to make a great commitment in this regard.

• Journal of The Korean Association of Information Education
• /
• v.11 no.2
• /
• pp.231-241
• /
• 2007

With a focus on LabView language to program Lego Mindstoms Robot in afterschool class to help children develop their special ability and aptitude. The purpose of this research was to make proposal for programming learning method using a robot as an algorithm learning tool to improve creative problem solving ability. To do this, robot programming training program in the amount of 30th period and teaching aids thereof were developed, and 6th grade primary school children were taught up to 30th period, then after, they were evaluated accordingly. Results from analysis of evaluation of achievement level with a focus on outcomes according to each period revealed that learners understood most of contents of curriculum. In view of such results from evaluation, it is judged that the curriculum as well as teaching aids that devised and created have been constituted in order that school children will be able to have developed a shared understanding of their learning sufficiently, and to put it into practice easily. Through these hands-on experiences in the course of researches, researcher could have confirmed the possibility of success for robot-programming training class as new creative algorithm learning tool in the primary school curriculum.

• Research in Community and Public Health Nursing
• /
• v.27 no.4
• /
• pp.410-422
• /
• 2016

Purpose: This study evaluated the effects of a cultural competence training program for public health nurses (PHNs) using intervention mapping. Methods: An embedded mixed method design was used. Forty-one PHNs (experimental: 21, control: 20) and forty marriage migrant women (MMW) (20, in each group) who were provided nursing care by PHN participated in the study. The experimental group was provided with a four-week cultural competence program consisting of an eight hour offline and online course, e-mail newsletters and social networking services (BAND). Transcultural Self-efficacy (TSE) of the PHNs, client-nurse trust, and satisfaction with nursing care of MMW were measured. Ten PHNs in the experimental group were interviewed after the experimental study. Results: The experimental group showed a significantly greater improvement in TSE, client-nurse trust, and satisfaction with nursing care than did the control group. Six themes emerged from qualitative data: (a) Recognizing cultural differences, (b) Being interested in the multicultural policy, (c) Trying to communicate in MMW's own language, (d) Providing medical information using internet and smart phone, (e) Embracing culturally diverse people into society, and (f) Requiring ongoing cultural competence training. Conclusion: Cultural competence training enabled PHNs to provide culturally competent care and contribute to MMW's health outcomes.