• Annual Conference on Human and Language Technology
• /
• 2016.10a
• /
• pp.300-304
• /
• 2016

본 논문에서는 한국어 의미역 결정을 순차열 분류 문제(Sequence Labeling Problem)가 아닌 순차열 변환 문제(Sequence-to-Sequence Learning)로 접근하였고, 구문 분석 단계와 자질 설계가 필요 없는 End-to-end 방식으로 연구를 진행하였다. 음절 단위의 RNN Search 모델을 사용하여 음절 단위로 입력된 문장을 의미역이 달린 어절들로 변환하였다. 또한 순차열 변환 문제의 성능을 높이기 위해 연구된 인풋-피딩(Input-feeding) 기술과 카피넷(CopyNet) 기술을 한국어 의미역 결정에 적용하였다. 실험 결과, Korean PropBank 데이터에서 79.42%의 레이블 단위 f1-score, 71.58%의 어절 단위 f1-score를 보였다.

• Journal of Korea Multimedia Society
• /
• v.22 no.2
• /
• pp.250-259
• /
• 2019

Big data processing technology and artificial intelligence (AI) are increasingly attracting attention. Natural language processing is an important research area of artificial intelligence. In this paper, we use Korean news articles to extract topic distributions in documents and word distribution vectors in topics through LDA-based Topic Modeling. Then, we use Word2vec to vector words, and generate a weight matrix to derive the relevance SCORE considering the semantic relationship between the words. We propose a way to recommend documents in order of high score.

• Journal of the Korean Chemical Society
• /
• v.66 no.5
• /
• pp.376-389
• /
• 2022

The purpose of this study was to investigate the effects of implementing semantic mapping reading strategy in the science class on high school students' science text reading ability. 3^rd grade students of science core high school in a small and medium-sized city participated in this study for a semester. Texts with socio-scientific issues and chemistry subjects were used to implement semantic mapping reading strategy in the science class. To investigate the changes in students' science text reading ability, experimental group students participated in the pre-reading and post-science reading ability tests and the results were analyzed. The results of this study showed that the mean of the science reading ability test score of experimental group was significantly higher than that of the comparison group. We found that drawing a semantic mapping before solving a reading task made it easier for students to find information and infer meaning from text. It can be seen that students also recognize that the semantic mapping is helpful in understanding the text because it is easy to understand the relationship between concepts by visualizing the content of the text, and can connect their background knowledge with the text content.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.25 no.3
• /
• pp.101-110
• /
• 1997

The purpose of this study was on suggesting what is the image and image formation factor of interior landscaping plants. For this purpose, the sixty interior landscaping plants were selected. Selected plants were classified into 9 groups by similar characteristics of plants, for example, leaf color and leaf pattern. Data analysis were performed by semantic differential scale method, mean score and multiple regression algorithm. The results are as follows, 1. Comparing with image assessment, group 9 got the highest score in all aspects. 2. Comparing with the image assessment of interior landscaping plants, the "impressive" image was obtained the highest score and "bright", "cool", "beautiful" and "fresh" were followed. 3. Multiple regression analysis was performed to clarify influence degree of the adjectives related to the beauty. The next adjectives were significant check points on assessing the beauty of interior landscaping plants. Also, Guzmania magnifical was investigated to have the most beautiful image with the results of preference analysis. Vriesea splendens, Cordyline terminalis Kunth 'Lilliput' and Peperomia sandersii were identified as considerably preferred plants. were identified as considerably preferred plants.

• Korean Journal of Biological Psychiatry
• /
• v.21 no.4
• /
• pp.175-181
• /
• 2014

Objectives It was the aim to examine the association of the thyroid-related hormones with cognitive function, depression, and subjective memory impairment in community-dwelling elders with questionable dementia. Methods The sample consisted of 399 community residents with 'questionable dementia' aged 60 or over in whom serum thyroid-related hormones [thyroid stimulating hormone (TSH) and thyroxine] had been assayed. Cognitive impairment was defined using the Korean version of the Consortium Establish a Registry for Alzheimer's Disease. Depression was diagnosed using the Korean version of Geriatric Depression Scale and subjective memory complaint (SMC) was checked using the subjective memory complaints questionnaire (SMCQ). Age, gender, education, and the presence of apolipoprotein E {\varepsilon}4 were included as covariates. Results There was a significant positive association between verbal fluency test (VFT) score and serum TSH levels (p = 0.01). There was a significant negative association between SMCQ total score and word list memory test (WLMT)(p = 0.002) or word list recall test (WLRT) score (p = 0.013). Conclusions Lower serum TSH levels were associated with semantic memory (VFT), and we found that SMC was associated with episodic memory (WLMT and WLRT) in this sample.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.4
• /
• pp.71-79
• /
• 2019

By using convolutional neural networks (CNNs) based on semantic segmentation, road surface damage detection has being studied. In order to generate the CNN model, it is essential to collect the input and the corresponding labeled images. Unfortunately, such collecting pairs of the dataset requires a great deal of time and costs. In this paper, we proposed a road surface damage detection technique based on semi-supervised learning using pseudo labels to mitigate such problem. The model is updated by properly mixing labeled and unlabeled datasets, and compares the performance against existing model using only labeled dataset. As a subjective result, it was confirmed that the recall was slightly degraded, but the precision was considerably improved. In addition, the $F_1-score$ was also evaluated as a high value.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_2
• /
• pp.685-694
• /
• 2022

Building information is essential for various urban spatial analyses. For this reason, continuous building monitoring is required, but it is a subject with many practical difficulties. To this end, research is being conducted to extract buildings from satellite images that can be continuously observed over a wide area. Recently, deep learning-based semantic segmentation techniques have been used. In this study, a part of the structure of the context-based ResU-Net was modified, and training was conducted to automatically extract a building from a 30 cm Worldview-3 RGB image using SpaceNet's building v2 free open data. As a result of the classification accuracy evaluation, the f1-score, which was higher than the classification accuracy of the 2nd SpaceNet competition winners. Therefore, if Worldview-3 satellite imagery can be continuously provided, it will be possible to use the building extraction results of this study to generate an automatic model of building around the world.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_2
• /
• pp.1579-1590
• /
• 2020

In this paper, spatially-adaptive denormalization (SPADE) based U-Net is proposed to detect changes by using high-resolution satellite images. The proposed network is to preserve spatial information using SPADE. Change detection methods using high-resolution satellite images can be used to resolve various urban problems such as city planning and forecasting. For using pixel-based change detection, which is a conventional method such as Iteratively Reweighted-Multivariate Alteration Detection (IR-MAD), unchanged areas will be detected as changing areas because changes in pixels are sensitive to the state of the environment such as seasonal changes between images. Therefore, in this paper, to precisely detect the changes of the objects that consist of the city in time-series satellite images, the semantic spatial objects that consist of the city are defined, extracted through deep learning based image segmentation, and then analyzed the changes between areas to carry out change detection. The semantic objects for analyzing changes were defined as six classes: building, road, farmland, vinyl house, forest area, and waterside area. Each network model learned with KOMPSAT-3A satellite images performs a change detection for the time-series KOMPSAT-3 satellite images. For objective assessments for change detection, we use F1-score, kappa. We found that the proposed method gives a better performance compared to U-Net and UNet++ by achieving an average F1-score of 0.77, kappa of 77.29.

• The KIPS Transactions:PartB
• /
• v.16B no.2
• /
• pp.173-180
• /
• 2009

The purpose of developing an automated scoring system for English composition is to score English writing tests and to give diagnostic feedback to the test-takers without human's efforts. The system developed through our research detects grammatical errors of a single sentence on morphological, syntactic and semantic stages, respectively, and those errors are calculated into the final score. The error detecting stages are independent from one another, which causes duplicating the identical errors with different labels at different stages. These duplicated errors become a hindering factor to calculating an accurate score. This paper presents a solution to detecting the duplicated errors and improving an accuracy in calculating the final score by eliminating one of the errors.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.10
• /
• pp.3972-3988
• /
• 2020

Existing methods always rely on statistical features to extract local words for microblog user geolocation. There are many non-local words in extracted words, which makes geolocation accuracy lower. Considering the statistical and semantic features of local words, this paper proposes a microblog user geolocation method by extracting local words based on word clustering and wrapper feature selection. First, ordinary words without positional indications are initially filtered based on statistical features. Second, a word clustering algorithm based on word vectors is proposed. The remaining semantically similar words are clustered together based on the distance of word vectors with semantic meanings. Next, a wrapper feature selection algorithm based on sequential backward subset search is proposed. The cluster subset with the best geolocation effect is selected. Words in selected cluster subset are extracted as local words. Finally, the Naive Bayes classifier is trained based on local words to geolocate the microblog user. The proposed method is validated based on two different types of microblog data - Twitter and Weibo. The results show that the proposed method outperforms existing two typical methods based on statistical features in terms of accuracy, precision, recall, and F1-score.