• Journal of KIISE:Software and Applications
• /
• v.33 no.3
• /
• pp.344-355
• /
• 2006

In daily activities, the interaction between humans and robots is very important for supporting the user's task effectively. Dialogue may be useful to increase the flexibility and facility of interaction between them. Traditional studies of robots have only dealt with simple queries like commands for interaction, but in real conversation it is more complex and various for using many ways of expression, so people can often omit some words relying on the background knowledge or the context of the discourse. Since the same queries can have various meaning by this reason, it is needed to manage this situation. In this paper we propose a method that uses hierarchical bayesian networks to implement mixed-initiative interaction for managing vagueness of conversation in the service robot. We have verified the usefulness of the proposed method through the simulation of the service robot and usability test.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.32 no.3
• /
• pp.247-264
• /
• 2021

This study aims to create a deep learning-based classification model to classify suicide tendency by suicide corpus constructed for the present study. Also, to analyze suicide factors, the study classified suicide tendency corpus into detailed topics by using topic modeling, an analysis technique that automatically extracts topics. For this purpose, 2,011 documents of the suicide-related corpus collected from social media naver knowledge iN were directly annotated into suicide-tendency documents or non-suicide-tendency documents based on suicide prevention education manual issued by the Central Suicide Prevention Center, and we also conducted the deep learning model(LSTM, BERT, ELECTRA) performance evaluation based on the classification model, using annotated corpus data. In addition, one of the topic modeling techniques, LDA identified suicide factors by classifying thematic literature, and co-word analysis and visualization were conducted to analyze the factors in-depth.

• Journal of The Korean Association of Information Education
• /
• v.25 no.3
• /
• pp.501-510
• /
• 2021

This paper was described to assess the possibility of field application of the developed textbooks by developing a textbook using action learning to conduct ICT electromagnetic waves training education for elementary and middle school teachers and applying it on a pilot basis. To this end, it was organized to be used in conjunction with classes in several subjects and provided various teaching materials to facilitate teachers' convenience to use the textbook. Also, the textbook was composed of a content structure of 10 sessions. As for the proposed textbook, the overall understanding of ICT electromagnetic waves was improved through pilot application in teacher training, and problem-solving ability, cooperative learning ability, democratic citizenship, and knowledge information processing ability were improved through action learning. It can be said that it contributed to improving the understanding of ICT electromagnetic waves and teachers' competencies.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.10
• /
• pp.73-82
• /
• 2009

This paper proposes a variance recovery method for character strokes that can be missed in applying the previously proposed color variance approach in text detection of natural scene images. The previous method has a shortcoming of missing the color variance due to the fixed length of horizontal and vertical windows of variance detection when the character strokes are thick or long. Thus, this paper proposes a variance recovery method by using geometric information of bounding boxes of connected components and heuristic knowledge. We have tested the proposed method using various kinds of document-style and natural scene images such as billboards, signboards, etc captured by digital cameras and mobile-phone cameras. And we showed the improved text detection accuracy even in the images of containing large characters.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.448-453
• /
• 2023

대규모 언어 모델 (Large Language Model, LLM)을 인간의 선호도 관점에서 평가하는 것은 기존의 벤치마크 평가와는 다른 도전적인 과제이다. 이를 위해, 기존 연구들은 강력한 LLM을 평가자로 사용하여 접근하였지만, 높은 비용 문제가 부각되었다. 또한, 평가자로서 LLM이 사용하는 주관적인 점수 기준은 모호하여 평가 결과의 신뢰성을 저해하며, 단일 모델에 의한 평가 결과는 편향될 가능성이 있다. 본 논문에서는 엄격한 기준을 활용하여 편향되지 않은 평가를 수행할 수 있는 평가 프레임워크 및 평가자 모델 'FubaoLM'을 제안한다. 우리의 평가 프레임워크는 심층적인 평가 기준을 통해 다수의 강력한 한국어 LLM을 활용하여 연쇄적 사고(Chain-of-Thought) 기반 평가를 수행한다. 이러한 평가 결과를 다수결로 통합하여 편향되지 않은 평가 결과를 도출하며, 지시 조정 (instruction tuning)을 통해 FubaoLM은 다수의 LLM으로 부터 평가 지식을 증류받는다. 더 나아가 본 논문에서는 전문가 기반 평가 데이터셋을 구축하여 FubaoLM 효과성을 입증한다. 우리의 실험에서 앙상블된 FubaoLM은 GPT-3.5 대비 16% 에서 23% 향상된 절대 평가 성능을 가지며, 이항 평가에서 인간과 유사한 선호도 평가 결과를 도출한다. 이를 통해 FubaoLM은 비교적 적은 비용으로도 높은 신뢰성을 유지하며, 편향되지 않은 평가를 수행할 수 있음을 보인다.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.2
• /
• pp.67-78
• /
• 2024

Amidst the onset of the Fourth Industrial Revolution and the prominence of artificial intelligence, societal structures are undergoing significant changes. There is a heightened global interest in AI education for nurturing future talents. Consequently, this research aims to develop an AI-integrated Korean language curriculum for first-year high school students, utilizing the ADDIE model for instructional program development. To assess the program's effectiveness, pre-post assessments were conducted on future core competencies (Collaboration, Communication, Critical Thinking, Creativity) and knowledge information processing skills. The curriculum, spanning nine sessions and incorporating four small projects, sought to provide students with a new experience of AI-integrated Korean language education. As a result, students who participated in the program demonstrated improvement in future core competencies across all areas, and positive outcomes were observed in satisfaction levels and qualitative analysis. Through these findings, it is suggested that this program successfully integrates artificial intelligence into high school Korean language education, potentially contributing to the cultivation of future talents among students.

• Journal of Korean Elementary Science Education
• /
• v.34 no.4
• /
• pp.502-518
• /
• 2015

In order to find out Elementary pre-service teachers' reflective thinking and experiment performance ability related with Photosynthesis Experiment in the Korea Elementary School Science Textbook, the research is conducted targeting Elementary pre-service teachers. They are asked to carry out the experiment and write their own report about the difficulties and solutions of exploration process. This study aims to analyze Elementary pre-service teachers' reflection and experiment performance ability on Photosynthesis experiment based on 10 groups' reports and presentation materials. Reflective thinking extracts 108 statements which is associated with the four types of the sentence 'Knowledge, Procedure, Orientation, Attitude' in 10 reports. There are many sentences about reflective thinking acquired through analysis of the photosynthesis experiment. reflective thinking about the newly discovered type or changed concepts through experimentation in Knowledge is at the highest frequency. 56 sentences in relation to the ability to perform experiments are extracted by adding 4 different types of reflective thinking in 10 groups shown the highest frequency group and the lowest frequency group's report through analyzing 4 steps 'Experimental preparation and safety accident prevention', 'Experiments performance', 'Experimental results and generalization', and 'Experimental results and feedback.' Results of the analysis showed that there are the biggest difference between the two groups in 'experiment results supplement and feedback step.' In the lowest group's report, there's no contents related with 'Computer-assisted information processing' in the 'Experimental results summary and generalization stage', 'Alternative reagents and materials research', and 'Devising alternative experiment methods'.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.2
• /
• pp.750-762
• /
• 2019

The importance of the call center as a contact point for the enterprise is growing. However, call centers have difficulty with their operating agents due to the agents' lack of knowledge and owing to frequent agent turnover due to downturns in the business, which causes deterioration in the quality of customer service. Therefore, through an N-bank call center case study, we developed a system to reduce the burden of keeping up business knowledge and to improve customer service quality. It is a "real-time agent advisor" system that provides agents with answers to customer questions in real time by combining AI technology for speech recognition, natural language processing, and questions & answers for existing call center information systems, such as a private branch exchange (PBX) and computer telephony integration (CTI). As a result of the case study, we confirmed that the speech recognition system for real-time call analysis and the corpus construction method improves the natural speech processing performance of the query response system. Especially with name entity recognition (NER), the accuracy of the corpus learning improved by 31%. Also, after applying the agent advisor system, the positive feedback rate of agents about the answers from the agent advisor was 93.1%, which proved the system is helpful to the agents.

• Knowledge Management Research
• /
• v.22 no.4
• /
• pp.27-40
• /
• 2021

Click-Through Rate (CTR) prediction is a key function that determines the ranking of candidate items in the recommendation system and recommends high-ranking items to reduce customer information overload and achieve profit maximization through sales promotion. The fields of natural language processing and image classification are achieving remarkable growth through the use of deep neural networks. Recently, a transformer model based on an attention mechanism, differentiated from the mainstream models in the fields of natural language processing and image classification, has been proposed to achieve state-of-the-art in this field. In this study, we present a method for improving the performance of a transformer model for CTR prediction. In order to analyze the effect of discrete and categorical CTR data characteristics different from natural language and image data on performance, experiments on embedding regularization and transformer normalization are performed. According to the experimental results, it was confirmed that the prediction performance of the transformer was significantly improved when the L2 generalization was applied in the embedding process for CTR data input processing and when batch normalization was applied instead of layer normalization, which is the default regularization method, to the transformer model.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.5
• /
• pp.429-437
• /
• 2022

Recently, the demand for a QA (Question Answering) system for human-machine communication has increased. Among the QA systems, a closed domain QA system that can handle spatial-related questions is called GeoQA. In this study, a new type of graph database, LPG (Labeled Property Graph) was used to overcome the limitations of the RDF (Resource Description Framework) based database, which was mainly used in the GeoQA field. In addition, GraphQL (Graph Query Language), an API-type query language, is introduced to address the fact that the LPG query language is not standardized and the GeoQA system may depend on specific products. In this study, database was built so that answers could be retrieved when spatial-related questions were entered. Each data was obtained from the national spatial information portal and local data open service. The spatial relationships between each spatial objects were calculated in advance and stored in edge form. The user's questions were first converted to GraphQL through FOL (First Order Logic) format and delivered to the database through the GraphQL server. The LPG used in the experiment is Neo4j, the graph database that currently has the highest market share, and some of the built-in functions and QGIS were used for spatial calculations. As a result of building the system, it was confirmed that the user's question could be transformed, processed through the Apollo GraphQL server, and an appropriate answer could be obtained from the database.