• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.382-387
• /
• 2023

현재 GPT-4와 같은 거대한 언어 모델이 기계 번역, 요약 및 대화와 같은 다양한 작업에서 압도적인 성능을 보이고 있다. 그러나 이러한 거대 언어 모델은 학습 및 적용에 상당한 계산 리소스와 도메인 특화 미세 조정이 어려운 등 몇 가지 문제를 가지고 있다. In-Context learning은 데이터셋에서 추출한 컨택스트의 정보만으로 효과적으로 작동할 수 있는 효율성을 제공하여 앞선 문제를 일부 해결했지만, 컨텍스트의 샷 개수와 순서에 민감한 문제가 존재한다. 이러한 도전 과제를 해결하기 위해, 우리는 Super In-Context Learning (SuperICL)을 활용한 새로운 방법론을 제안한다. 기존의 SuperICL은 적용한 플러그인 모델의 출력 정보를 이용하여 문맥을 새로 구성하고 이를 활용하여 거대 언어 모델이 더욱 잘 분류할 수 있도록 한다. Super In-Context Learning for Generation은 다양한 자연어 생성 작업에 효과적으로 최적화하는 방법을 제공한다. 실험을 통해 플러그인 모델을 교체하여 다양한 작업에 적응하는 가능성을 확인하고, 자연어 생성 작업에서 우수한 성능을 보여준다. BLEU 및 ROUGE 메트릭을 포함한 평가 결과에서도 성능 향상을 보여주며, 선호도 평가를 통해 모델의 효과성을 확인했다.

• Educational Technology International
• /
• v.6 no.2
• /
• pp.59-67
• /
• 2005

The primary purposes of this study are to develop a Situated Learning Support System based on an MMORPG (Massively Multiplayer Online Role Playing Game) and to investigate applications of Situated Learning theory both hypothetically and practically. In Situated Leaning theory, cognition is interpreted as a dynamic system related to situation, context and activity. According to this theory, learning context, social interaction and personal direct experience are also emphasized. A virtual reality learning system based on an MMORPG provides context, social interaction and a learning environment able to provide direct experiences. However, such a system has been difficult for teachers to develop. This study aims to develop a support system facilitating the construction of a Situated Learning System based on an MMORPG. This study proposes new research and practical applications of Situated Learning theory using educational games.

• Journal of Korea Multimedia Society
• /
• v.24 no.10
• /
• pp.1391-1402
• /
• 2021

This paper focuses use context-sensitive spelling error correction using generative adversarial network. Generative adversarial network[1] are attracting attention as they solve data generation problems that have been a challenge in the field of deep learning. In this paper, sentences are generated using word embedding information and reflected in word distribution representation. We experiment with DCGAN[2] used for the stability of learning in the existing image processing and D2GAN[3] with double discriminator. In this paper, we experimented with how the composition of generative adversarial networks and the change of learning corpus influence the context-sensitive spelling error correction In the experiment, we correction the generated word embedding information and compare the performance with the actual word embedding information.

• The KIPS Transactions:PartD
• /
• v.14D no.1 s.111
• /
• pp.139-144
• /
• 2007

In seeking to improve the workload efficiency and inference capability of context-aware systems, we propose a new framework for an advanced teaming mechanism that uses improved bath propagation (BP) algorithm. Even though a learning mechanism is one of the most important parts in a context-aware system, the existing algorithms focused on facilitating systems by elaborating the learning mechanism with user's context information are rare. BP is the most adaptable algorithm for learning mechanism of context-aware systems. By using the improved BP algorithm, the framework we proposed drastically improves the inference capability so that the overall performance is far better than other systems. Also, using the special system cache, the framework manages the workload efficiently. Experiments show that there is an obvious improvement in overall performanre of the context-awareness systems using the proposed framework.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.5
• /
• pp.674-677
• /
• 2020

The cultural background of users utilizing image search engines has a significant impact on the satisfaction of the search results. Therefore, it is important to analyze and understand the cultural context of images for more accurate image search. In this paper, we investigate how the cultural context of images can affect the performance of image classification. To this end, we first collected various types of images (e.g,. food, temple, etc.) with various cultural contexts (e.g., Korea, Japan, etc.) from web search engines. Afterwards, a deep transfer learning approach using VGG19 and MobileNetV2 pre-trained with ImageNet was adopted to learn the cultural features of the collected images. Through various experiments we show the performance of image classification can be differently affected according to the cultural context of images.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1072-1075
• /
• 2005

This paper presents that TD method is applied to the human adaptive devices for smart home with context awareness (or recognition) technique. For smart home, the very important problem is how the appliances (or devices) can adapt to user. Since there are many humans to manage home appliances (or devices), managing the appliances automatically is difficult. Moreover, making the users be satisfied by the automatically managed devices is much more difficult. In order to do so, we can use several methods, fuzzy controller, neural network, reinforcement learning, etc. Though the some methods could be used, in this case (in dynamic environment), reinforcement learning is appropriate. Among some reinforcement learning methods, we select the Temporal Difference learning method as a core algorithm for adapting the devices to user. Since this paper assumes the environment is a smart home, we simply explained about the context awareness. Also, we treated with the TD method briefly and implement an example by VC++. Thereafter, we dealt with how the devices can be applied to this problem.

• Journal of The Korean Association For Science Education
• /
• v.15 no.3
• /
• pp.325-331
• /
• 1995

The purpose of this study is to analyze learning objectives of biology contents in SATIS 14-16. Modified the 5th NAEP three dimentional science assessment framework was used to analyze learning objectives of SATIS 14-16. This study will be a basic data for the development of STS programs in KOREA. The following results were obtained. 1. In a content dimension, 'structures and functions of organism'(63.9%) was the most frequently found, followed by 'the nature and our Iives'(22.1%), 'a continuity of Iife'(9.4%) and 'our surrounding Iives'(4.7%). 2. In a cognitive dimension, an understanding of scientific knowledge(32.7%) was the most frequently found, followed by an improvement of inquiry ability(25.6%), attitude(24.7%), and scientific knowledge and its application(17.0%). 3. In a context dimension, a personal context(32.8%) was the most frequently found, followed by a social context(27.3%), a scientific context(20.0%) and a technological context(20.0%). 4. There were some differences in behavior when each content was compared. In 'surrounding lives' and 'a continuity of life', an understanding of scientific knowledge was the most frequently found. In 'structures and functions of organism' and 'the nature and our lives', proportions of four behavioral catagories were relatively even. 5. There were some differences in context when each content was compared. In 'surrounding lives', scientific context was the most frequently found, whereas in 'structures and functions of lives', individual context was found the most frequently. In 'a continuity of life', scientific and social context were found more frequently than others. In 'the nature and our lives', social context was the most frequent one.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.4
• /
• pp.9-21
• /
• 2024

Deep learning has been developing rapidly in recent years, with many researchers working to utilize large language models in various domains. However, there are practical difficulties that developing and utilizing language models require massive data and high-performance computing resources. Therefore, in-context learning, which utilizes prompts to learn efficiently, has been introduced, but there needs to be clear criteria for effective prompts for learning. In this study, we propose a methodology for enhancing prompt-based learning performance by improving the PET technique, which is one of the contextual learning methods, to select PVPs that are similar to the context of existing data. To evaluate the performance of the proposed methodology, we conducted experiments with 30,100 restaurant review datasets collected from Yelp, an online business review platform. We found that the proposed methodology outperforms traditional PET in all aspects of accuracy, stability, and learning efficiency.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.22.3-22
• /
• 2001

An attention task, in which context information should be extracted from the first presented pattern, and the recognition answer of the second presented pattern should be generated using the context information, is employed in this paper. An Elman-type recurrent neural network is utilized to extract and keep the context information. A reinforcement signal that indicates whether the answer is correct or not, is only a signal that the system can obtain for the learning. Only by this learning, necessary context information became to be extracted and kept, and the system became to generate the correct answers. Furthermore, the function of an associative memory is observed in the feedback loop in the Elman-type neural network.

• Korean Journal of Child Studies
• /
• v.36 no.1
• /
• pp.1-17
• /
• 2015

The purpose of this research was to explore the influence of a mother's motivational beliefs in the context of the child education and parent-teacher relationship and the impact that it has on the learning related skills of young children. The participants in this study consisted of 243 mothers of 4~5 years old children and 20 teachers in 5 child education centers located in Seoul, Korea. The data was analyzed by means of using statistical method such as mean, standard deviation, t-test, Pearson correlation, and stepwise regression. The major findings of this study were as follows: First, there were significant differences between parent-teacher relationship and learning related skills of young children according to the children's sex and maternal educational level. Second, children's sex, maternal educational level, and the parent-teacher relationship were significantly related with the learning related skills of young children. Last, mother's motivational beliefs in the context of child education and the parent-teacher relationship directly influenced the learning related skills of young children. The results of this study suggest that positive parent-teacher relationships are important for developing the learning related skills of young children and this in turn can predict the level of children's adjustment and success in school.