• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.537-540
• /
• 2018

우리는 단어 임베딩에 외부지식을 내재할 수 있는 Ontofitting 방법을 제안한다. 이 방법은 retrofitting의한 방법으로 유의어, 반의어, 상위어, 하위어 정보를 단어 임베딩에 내재할 수 있다. 유의어와 반의어 정보를 내재하기 위해서 벡터의 각 유사도를 사용하였고 상하위어 정보를 내재하기 위해서 벡터의 길이 정보를 사용하였다. 유의어 사이에는 작은 각도를 가지고 반의어 사이에는 큰 각도를 가지게 된다. 하위어는 상위어보다 상대적으로 작은 길이를 가지게 된다. SimLex와 HyperLex로 실험하여 효과와 안정성을 검증하였다. 의미정보를 내재한 임베딩을 사용할 수 있다면 QA, 대화 등 응용에서 보다 좋은 성능을 보일 수 있을 것이다.

• Journal of Korea Multimedia Society
• /
• v.23 no.4
• /
• pp.549-557
• /
• 2020

Chinese is the most spoken language in the world. However, because Chinese is a hieroglyphic language, using Chinese in a digital environment is very inconvenient. Chinese users are using Pinyin for Chinese input, but the phonetic representation of the Latin alphabet is not good. Hunminjeongeum has an excellent phonetic representation which can improve Chinese usage in digital environment. Therefore, it is possible to improve the use of Chinese by Chinese users in digital environment and to help Korean users who are learning Chinese. Therefore, this paper proposes a Chinese input method using Hunminjeongeum. In addition, we develop an input software using this input method and verify its effectiveness by evaluating usability.

• Research in Mathematical Education
• /
• v.15 no.1
• /
• pp.15-30
• /
• 2011

We study to design educational Logo-based microworld environment equipped with 3D construction capability, 3D manipulation, and web-based communication. Extending the turtle metaphor of 2D Logo, we design simple and intuitive symbolic representation system that can create several turtle objects and operations. We also present various mathematization activities applying the turtle objects and suggest the way to make good use of them in mathematics education. In our microworld environment, the symbolic representations constructing the turtle objects can be used for web-based collaborative learning, communication, and assessments.

• Journal of Elementary Mathematics Education in Korea
• /
• v.15 no.1
• /
• pp.161-178
• /
• 2011

For the students who live in the knowledge-information oriented society, thinking rationally and training mathematical communication ability are necessary. I represented three ways of teaching-learning related to mathematical communication in revised 2006 curriculum of elementary mathematics. In this study, based on three matters from devised curriculum, I have done survey-analysis of mathematical representation and characteristics of contents of major theses about mathematical communication published after 2007 curriculum revision, for further mathematical communication teaching.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.7C
• /
• pp.428-434
• /
• 2011

Recently, subspace analysis has raised its performance to a higher level through the adoption of kernel-based nonlinearity. Especially, the radial basis function, based on its nonparametric nature, has shown promising results in face recognition. However, due to the endemic small sample size problem of face data, the conventional kernel-based feature extraction methods have difficulty in data representation. In this paper, we introduce a novel variant of the RBF kernel to alleviate this problem. By adopting the concept of the nearest feature line classifier, we show both effectiveness and generalizability of the proposed method, particularly regarding the small sample size issue.

• Journal of Information Processing Systems
• /
• v.15 no.6
• /
• pp.1449-1461
• /
• 2019

Face sketch synthesis plays an important role in public security and digital entertainment. In this paper, we present a novel face sketch synthesis method via local similarity and nonlocal similarity regularization terms. The local similarity can overcome the technological bottlenecks of the patch representation scheme in traditional learning-based methods. It improves the quality of synthesized sketches by penalizing the dissimilar training patches (thus have very small weights or are discarded). In addition, taking the redundancy of image patches into account, a global nonlocal similarity regularization is employed to restrain the generation of the noise and maintain primitive facial features during the synthesized process. More robust synthesized results can be obtained. Extensive experiments on the public databases validate the generality, effectiveness, and robustness of the proposed algorithm.

• International Journal of Advanced Culture Technology
• /
• v.9 no.1
• /
• pp.218-223
• /
• 2021

Pervasive enhancement and required enforcement of the Internet of Things (IoTs) in a distributed massively multiplayer online architecture have effected in massive growth of Big-Data in terms of server over-load. There have been some previous works to overcome the overloading of server works. However, there are lack of considered methods, which is commonly applicable. Therefore, we propose a combing Sparse Auto-Encoder and Load-Balancing, which is ProGReGA for Big-Data of server loads. In the process of Sparse Auto-Encoder, when it comes to selection of the feature-pattern, the less relevant feature-pattern could be eliminated from Big-Data. In relation to Load-Balancing, the alleviated degradation of ProGReGA can take advantage of the less redundant feature-pattern. That means the most relevant of Big-Data representation can work. In the performance evaluation, we can find that the proposed method have become more approachable and stable.

• ETRI Journal
• /
• v.44 no.2
• /
• pp.327-338
• /
• 2022

Classification models for human action recognition require robust features and large training sets for good generalization. However, data augmentation methods are employed for imbalanced training sets to achieve higher accuracy. These samples generated using data augmentation only reflect existing samples within the training set, their feature representations are less diverse and hence, contribute to less precise classification. This paper presents new data augmentation and action representation approaches to grow training sets. The proposed approach is based on two fundamental concepts: virtual video generation for augmentation and representation of the action videos through robust features. Virtual videos are generated from the motion history templates of action videos, which are convolved using a convolutional neural network, to generate deep features. Furthermore, by observing an objective function of the genetic algorithm, the spatiotemporal features of different samples are combined, to generate the representations of the virtual videos and then classified through an extreme learning machine classifier on MuHAVi-Uncut, iXMAS, and IAVID-1 datasets.

• Journal of Korea Multimedia Society
• /
• v.25 no.8
• /
• pp.1203-1211
• /
• 2022

Melanoma is a skin cancer that starts in pigment-producing cells (melanocytes). The death rates of skin cancer like melanoma can be reduced by early detection and diagnosis of diseases. It is common for doctors to spend a lot of time trying to distinguish between skin lesions and healthy cells because of their striking similarities. The detection of melanoma lesions can be made easier for doctors with the help of an automated classification system that uses deep learning. This study presents a new approach for melanoma classification based on an ensemble of deep convolution neural networks and a Log-Gabor filter. First, we create the Log-Gabor representation of the original image. Then, we input the Log-Gabor representation into a new ensemble of deep convolution neural networks. We evaluated the proposed method on the melanoma dataset collected at Yonsei University and Dongsan Clinic. Based on our numerical results, the proposed framework achieves more accuracy than other approaches.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.115-121
• /
• 2022

질문에 답하기 위해 관련 구절을 검색하는 기술은 오픈 도메인 질의응답의 검색 단계를 위해 필요하다. 전통적인 방법은 정보 검색 기법인 빈도-역문서 빈도(TF-IDF) 기반으로 희소한 벡터 표현을 활용하여 구절을 검색한다. 하지만 희소 벡터 표현은 벡터 길이가 길 뿐만 아니라, 질문에 나오지 않는 단어나 토큰을 검색하지 못한다는 취약점을 가진다. 밀집 벡터 표현 연구는 이러한 취약점을 개선하고 있으며 대부분의 연구가 영어 데이터셋을 학습한 것이다. 따라서, 본 연구는 한국어 데이터셋을 학습한 밀집 벡터 표현을 연구하고 여러 가지 부정 샘플(negative sample) 추출 방법을 도입하여 전이 학습한 모델 성능을 비교 분석한다. 또한, 대화 응답 선택 태스크에서 밀집 검색에 활용한 순위 재지정 상호작용 레이어를 추가한 실험을 진행하고 비교 분석한다. 밀집 벡터 표현 모델을 학습하는 것이 도전적인 과제인만큼 향후에도 다양한 시도가 필요할 것으로 보인다.