• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.211-214
• /
• 2020

Abstract Meaning Representation(AMR)은 문장의 의미를 그래프 구조로 인코딩하여 표현하는 의미 형식표현으로 문장의 각 노드는 사건이나 개체를 취급하는 개념으로 취급하며 간선들은 이러한 개념들의 관계를 표현한다. AMR 파싱은 주어진 문장으로부터 AMR 그래프를 생성하는 자연어 처리 태스크이다. AMR 그래프의 각 개념은 추상 표현으로 문장 내의 토큰과 명시적으로 정렬되지 않는 어려움이 존재한다. 이러한 문제를 해결하기 위해 별도의 사전 학습된 정렬기를 이용하여 해결하거나 별도의 정렬기 없이 Sequence-to-Sequence 계열의 모델로 입력 문장으로부터 그래프의 노드를 생성하는 방식으로 연구되어 왔다. 본 논문에서는 문장의 입력 시퀀스와 부분 생성 그래프 사이에서 반복 추론을 통해 새로운 노드와 기존 노드와의 관계를 구성하여 점진적으로 그래프를 구성하는 모델을 한국어 AMR 데이터 셋에 적용하여 Smatch 점수 39.8%의 실험 결과를 얻었다.

• Annual Conference on Human and Language Technology
• /
• 2017.10a
• /
• pp.288-293
• /
• 2017

교수-학습 발화는 발화 턴 간에 규칙화된 인과관계가 강하고 자연 발화에서의 출현율이 낮다. 일반적으로 어휘부, 표현 제시부, 대화부로 구성되며 커리큘럼과 화제에 따라 구축된 언어자원이 필요하다. 기존의 말뭉치는 이러한 교수-학습 발화의 특징을 반영하지 않았기 때문에 한국어 교육용 튜터링 챗봇을 개발하는데에 활용도가 떨어진다. 이에 따라 이 논문에서는 자연스러운 언어 사용 수집, 도구 기반의 수집, 주제별 수집 및 분류, 점진적 구축 절차의 원칙에 따라 교수-학습의 실제 상황을 반영하는 준구어 말뭉치를 구축한다. 교실에서 발생하는 언어학습 상황을 시나리오로 구성하여 대화 흐름을 제어하고 채팅용 메신저와 유사한 형태의 도구를 통해 말뭉치를 구축한다. 이 연구는 한국어 튜터링 챗봇을 개발하기 위해 말뭉치 구축용 챗봇과 한국어 학습자, 한국어 교수자가 시나리오를 기반으로 발화문을 생성한 준구어 말뭉치를 최초로 구축한다는 데에 의의가 있다.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.9
• /
• pp.77-81
• /
• 2016

Logistic regression (LR) has been widely used for predicting the relationships among variables in various fields. We propose a new logistic regression model with a fine-grained weighting method, called value weighted logistic regression, by assigning different weights to each feature value. A gradient approach is utilized to obtain the optimal weights of feature values. We conduct experiments on several data sets and the experimental results show that the proposed method shows meaningful improvement in prediction accuracy.

• Journal of KIISE
• /
• v.43 no.11
• /
• pp.1270-1274
• /
• 2016

Logistic regression is widely used for predicting and estimating the relationship among variables. We propose a new logistic regression model, the value weighted logistic regression, which comprises of a fine-grained weighting method, and assigns adapted weights to each feature value. This gradient approach obtains the optimal weights of feature values. Experiments were conducted on several data sets from the UCI machine learning repository, and the results revealed that the proposed method achieves meaningful improvement in the prediction accuracy.

• Journal of The Korean Association For Science Education
• /
• v.22 no.4
• /
• pp.796-805
• /
• 2002

This study examined the knowledge structure constructed by children before formal instruction, and successive changes in the structural complexity of knowledge during and after the learning of 'Structure and Function of Plant' unit. It also investigated how those changes were affected by children's learning modes. The researchers made the 5th graders draw the first draft of their concept map to see the pre-existing knowledge structure concerned with the unit and four more concept maps after completing every fourth lesson. And to see how long their knowledge structures were preserved, the researchers made children draw additional concept maps in 3 days, 3 months, and 7 months after completing the unit. Children drew their current concept maps on the basis of the previous one while learning the unit and without the previous one after completing the unit. Each concept map drawn by children showed the degree of their current understanding on the structures and functions of plants. The results revealed that only two levels of hierarchy and five relationships among the components of the first concept map(relationship, hierarchy, cross link and example) were proven to be valid in terms of conceptual relevance. Growth in the structural complexity of knowledge took place progressively throughout the unit and the effects of learning mode on the growth were favorably reflected in concept map scores of meaningful learners over time(relationship, cross link, example: p<.01, hierarchy: p<.05). Although there were some differences on the concept map scores between two types of learners, they commonly showed that knowledge restructuring had occurred apparently in the early periods from the 1st to the 6th lesson and had not occurred at all in the last period of the unit. The frequency of tuning was higher in rote learners than in meaningful learners throughout the unit, but the frequency of accretion was reverse. Concept map scores of rote learners constructed in the course of learning of the unit decreased little by little gradually in all the categories after completing the unit. However, the average total map score of meaningful learners increased a little more in 7 months than in 3 months after completing the unit. Therefore it can be inferred that meaningful learners construct more stable and well-differentiated knowledge structures than the rote learners.

• The KIPS Transactions:PartB
• /
• v.10B no.3
• /
• pp.297-304
• /
• 2003

Nowdays, with the explosive growth of the web information, web users Increase requests of systems which collect and analyze web pages that are relevant. The systems which were develop to solve the request were used clustering methods to improve the duality of information. Clustering is defining inter relationship of unordered data and grouping data systematically. The systems using clustering provide the grouped information to the users. So, they understand the information efficiently. We proposed a hybrid clustering method to cluster a large quantity of data efficiently. By that method, We generate initial clusters using COBWEB Algorithm and refine them using Ezioni Algorithm. This paper adds two ideas in prior hybrid clustering method to increment accuracy and efficiency of clusters. Firstly, we propose the clustering method considering weight of attributes of data. Second, we redefine evaluation functions which generate initial clusters to increase efficiency in clustering. Clustering method proposed in this paper processes a large quantity of data and diminish of dependancy on sequence of input of data. So the clusters are useful to make user profiles in high quality. Ultimately, we will show that the proposed clustering method outperforms the pervious clustering method in the aspect of precision and execution speed.

• Journal of KIISE:Software and Applications
• /
• v.36 no.10
• /
• pp.816-824
• /
• 2009

In the face space, face images due to illumination and pose variations have a nonlinear distribution. Active Appearance Models (AAM) based on the linear model have limits to the nonlinear distribution of face images. In this paper, we assume that a few clusters of face images are given; we build local AAMs according to the clusters of face images, and then select a proper AAM model during the fitting phase. To solve the problem of updating fitting parameters among the models due to the model changing, we propose to build in advance relationships among the clusters in the parameter space from the training images. In addition, we suggest a gradual model changing to reduce improper model selections due to serious fitting failures. In our experiment, we apply the proposed model to Yale Face Database B and compare it with the previous method. The proposed method demonstrated successful fitting results with strongly illuminated face images of deep shadows.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.11
• /
• pp.672-682
• /
• 2020

The Korea Nowadays, which is research on digital twin technology for efficient operation in various industrial/manufacturing sites, is being actively conducted, and gradual depletion of fossil fuels and environmental pollution issues require new renewable/eco-friendly power generation methods, such as wave power plants. In wave power generation, however, which generates electricity from the energy of waves, it is very important to understand and predict the amount of power generation and operational efficiency factors, such as breakdown, because these are closely related by wave energy with high variability. Therefore, it is necessary to derive a meaningful correlation between highly volatile data, such as wave height data and sensor data in an oscillating water column (OWC) chamber. Secondly, the methodological study, which can predict the desired information, should be conducted by learning the prediction situation with the extracted data based on the derived correlation. This study designed a workflow-based training model using a machine learning framework to predict the pressure of the OWC. In addition, the validity of the pressure prediction analysis was verified through a verification and evaluation dataset using an IoT sensor data to enable smart operation and maintenance with the digital twin of the wave generation system.

• Journal of radiological science and technology
• /
• v.36 no.2
• /
• pp.99-110
• /
• 2013

In the medical field, the necessity of education growth for the professional Radiation Technologists has been emphasized to become experts on radiation and the radiation field is important of the society. Also, in hospitals and companies, important on thesis is getting higher in order to active and cope with rapidly changing internal and external environment and a more in-depth expert training, the necessity of new teaching and learning model that can cope with changes in a more proactive has become. Thesis writing classes brought limits to the in-depth learning as to start a semester and rely on only specific programs besides, inevitable on passive participation. In addition, it does not have a variety opportunity to present, an actual opportunity that can be written and discussed does not provide much caused by instructor-led classes. As well as, it has had a direct impact on the quality of the thesis, furthermore, having the opportunity to participate in various conferences showed the limitations. In order to solve these problems, in this study, writing thesis has organized training operations as a consistent gradual deepening of learning, at the same time, the operational idea was proposed based on the connectivity integrated operating and effective training program & instructional tool for improving the ability to perform the written actual thesis. The development of teaching and learning model consisted of 4 system modeling, scaffolding, articulation, exploration. Depending on the nature of the course, consisting team following the personal interest and the topic allow for connection subject, based on this, promote research capacity through a step-by-step evaluation and feedback and, fundamentally strengthen problem-solving skills through the journal studies, help not only solving the real-time problem by taking wiki-space but also efficient use of time, increase the quality of the thesis by activating cooperation through mentoring, as a result, it was to promote a positive partnership with the academic. Support system in three stages planning subject, progress & writing, writing thesis & presentation and based on cognitive apprenticeship. The ongoing Coaching and Reflection of professor and expert was applied in order to maintain these activities smoothly. The results of this study will introduce actively, voluntarily and substantially join to learners, by doing so, culture the enhancement of creativity, originality and the ability to co-work and by enhance the expertise of based-knowledge, it is considered to be help to improve the comprehensive ability.

• Journal of Korean Home Economics Education Association
• /
• v.16 no.4 s.34
• /
• pp.81-94
• /
• 2004

The purpose of this study was to research middle school students' interest and practice about the housing education contents in Technology and Home Economics Subject(classify them into three units, application of living space, indoor environment and equipments. support and repair of housing) in their real life. This was the investigation of which 529 middle school students have lived in Jeonbuk province, SPSS program was utilized to analyze percentage. mean and standard deviation. as well as t-test, One-Way ANOVA and Pearson's correlation coefficients. The results of this research were as follows: Middle school students' interest and practice of the housing education contents appeared to the middle level. Middle school students was consider that the order of interest parts of housing contents were indoor environment and equipments. application of living space, support and repair of housing. And the order of practice parts of housing contents were application of living space. indoor environment and equipments. support and repair of housing. There were significant differences in interest and practice of contents according to demographic variables such as sex, educational level of parents, social status of home. school record. Interest about the housing education contents had significant positive relationships with practices of contents of housing education. Therefore. it would be necessary to develop teaching materials and housing education contents promoting interest of students.