• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.12-17
• /
• 2019

FAQ(Frequently Asked Questions) 질의 응답 시스템은 자주 묻는 질문과 답변을 정의하고, 사용자 질의에 대해 정의된 답변 중 가장 알맞는 답변을 추론하여 제공하는 시스템이다. 정의된 대표 질문 및 대응하는 답변을 클래스(Class)라고 했을 때, FAQ 질의 응답 시스템은 분류(Classification) 문제라고 할 수 있다. 종래의 FAQ 분류는 동일 클래스 내 동의 문장(Paraphrase)에서 나타나는 공통적인 특징을 통해 분류 문제를 학습하였으나, 이는 비슷한 단어 구성을 가지면서 한 두 개의 단어에 의해 의미가 다른 문장의 차이를 구분하지 못하며, 특히 서로 다른 클래스에 속한 학습 데이터 간에 비슷한 의미를 가지는 문장이 존재할 때 클래스 분류에 오류가 발생하기 쉬운 문제점을 가지고 있다. 본 논문에서는 이 문제점을 해결하고자 서로 다른 클래스 내의 학습 데이터 문장들이 상이한 클래스임을 구분할 수 있도록 클래스 일치 여부(Class coincidence classification) 문제를 결합 학습(Jointly learning)하는 기법을 제안한다. 동일 클래스 내 학습 문장의 무작위 쌍(Pair)을 생성 및 학습하여 해당 쌍이 같은 클래스에 속한다는 것을 학습하게 하면서, 동시에 서로 다른 클래스 간 학습 문장의 무작위 쌍을 생성 및 학습하여 해당 쌍은 상이한 클래스임을 구분해 내는 능력을 함께 학습하도록 유도하였다. 실험을 위해서는 최근 발표되어 자연어 처리 분야에서 가장 좋은 성능을 보이고 있는 BERT 의 텍스트 분류 모델을 이용했으며, 제안한 기법을 적용한 모델과의 성능 비교를 위해 한국어 FAQ 데이터를 기반으로 실험을 진행했다. 실험 결과, 분류 문제만 단독으로 학습한 BERT 기본 모델보다 본 연구에서 제안한 클래스 일치 여부 결합 학습 모델이 유사한 문장들 간의 차이를 구분하며 유의미한 성능 향상을 보인다는 것을 확인할 수 있었다.

• Journal of The Korean Association of Information Education
• /
• v.9 no.2
• /
• pp.231-241
• /
• 2005

There are two main purposes in learning map in the subject of social studies in understanding the map itself and growing the ability of construing connection and situation and reasoning by applying the map. However, the map learning leans to understanding the map itself in existing materials. Although there is an interaction between learners and the context, there is hardly any interaction between learners or between teachers. Therefore, this paper designs and implements the web-based map learning system using the constructivism to make the cooperative study possible through the interaction and to be able to teach the map learning based on learners. The characteristics of the system suggested in this paper are as below. First, learners study the basic factors of the map by themselves and enable them to give feedbacks after the evaluation. Also, it embodies to evaluate the context of study as a multiple question after studying the whole thing. Second, the participation is induced by bringing the interests of learners based on the web and the interaction between teacher and learner as well as between learners is strengthened by the bulletin board and chatting function. Third, the study of utilizing map is embodied by means of applying the study model of solving problems and suggesting useful tasks.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.39 no.3
• /
• pp.18-31
• /
• 2002

In this study, we introduce a concept of advanced neurofuzzy polynomial networks(ANFPN), a hybrid modeling architecture combining neurofuzzy networks(NFN) and polynomial neural networks(PNN). These networks are highly nonlinear rule-based models. The development of the ANFPN dwells on the technologies of Computational Intelligence(Cl), namely fuzzy sets, neural networks and genetic algorithms. NFN contributes to the formation of the premise part of the rule-based structure of the ANFPN. The consequence part of the ANFPN is designed using PNN. At the premise part of the ANFPN, NFN uses both the simplified fuzzy inference and error back-propagation learning rule. The parameters of the membership functions, learning rates and momentum coefficients are adjusted with the use of genetic optimization. As the consequence structure of ANFPN, PNN is a flexible network architecture whose structure(topology) is developed through learning. In particular, the number of layers and nodes of the PNN are not fixed in advance but is generated in a dynamic way. In this study, we introduce two kinds of ANFPN architectures, namely the basic and the modified one. Here the basic and the modified architecture depend on the number of input variables and the order of polynomial in each layer of PNN structure. Owing to the specific features of two combined architectures, it is possible to consider the nonlinear characteristics of process system and to obtain the better output performance with superb predictive ability. The availability and feasibility of the ANFPN are discussed and illustrated with the aid of two representative numerical examples. The results show that the proposed ANFPN can produce the model with higher accuracy and predictive ability than any other method presented previously.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.4
• /
• pp.343-350
• /
• 2000

In this paper, we propose the Multi-FPNN(Fuzzy Polynomial Neural Networks) model based on FNN and PNN(Polyomial Neural Networks) for optimal system identifacation. Here FNN structure is designed using fuzzy input space divided by each separated input variable, and urilized both in order to get better output performace. Each node of PNN structure based on GMDH(Group Method of Data handing) method uses two types of high-order polynomials such as linearane and quadratic, and the input of that node uses three kinds of multi-variable inputs such as linear and quadratic, and the input of that node and Genetic Algorithms(GAs) to identify both the structure and the prepocessing of parameters of a Multi-FPNN model. Here, HCM clustering method, which is carried out for data preproessing of process system, is utilized to determine the structure method, which is carried out for data preprocessing of process system, is utilized to determance index with a weighting factor is used to according to the divisions of input-output space. A aggregate performance inddex with a wegihting factor is used to achieve a sound balance between approximation and generalization abilities of the model. According to the selection and adjustment of a weighting factor of this aggregate abjective function which it is acailable and effective to design to design and optimal Multi-FPNN model. The study is illustrated with the aid of two representative numerical examples and the aggregate performance index related to the approximation and generalization abilities of the model is evaluated and discussed.

• Korean Journal of Food Science and Technology
• /
• v.40 no.6
• /
• pp.691-695
• /
• 2008

The objective of this study was to evaluate the effects of glycoprotein isolated from Morus indica L. (MIL) on plasma cholesterol levels and on the activities of hepatic detoxicant enzymes in ICR mice. MIL glycoprotein evidenced good scavenging activities against lipid peroxyl radicals. When the mice were treated with Triton WR-1339, the levels of total cholesterol (TC) and low-density lipoprotein (LDL)-cholesterol in plasma increased significantly by 53.9 and 47.5 mg/dL, respectively, as compared to the controls. However, when pretreated with MIL glycoprotein $(100{\mu}g/mL)$, ICR mice showed marked reductions to 55.4 and 47.0 mg/dL, as compared to Triton WR-1339 treatment alone. Interestingly, high density lipoprotein cholesterol levels were unchanged. These results indicate that the MIL glycoprotein is capable of scavenging lipidperoxyl radicals, lowering plasma lipid levels, and increasing the activities of detoxicant enzymes in the mouse liver.

• Journal of Veterinary Clinics
• /
• v.24 no.2
• /
• pp.77-81
• /
• 2007

Diagnostic performance of polymerase chain reaction (PCR) for detecting Dirofilaria immitis in dogs was evaluated when no gold standard test was employed. An enzyme-linked immunosorbent assay test kit (SnapTM, IDEXX, USA) with unknown parameters was also employed. The sensitivity and specificity of the PCR from two-population model were estimated by using both maximum likelihood using expectation-maximization (EM) algorithm and Bayesian method, assuming conditional independence between the two tests. A total of 266 samples, 133 samples in each trial, were randomly retrieved from the heartworm database records during the year 2002-2004 in a university animal hospital. These data originated from the test results of military dogs which were brought for routine medical check-up or testing for heartworm infection. When combined 2 trials, sensitivity and specificity of the PCR was 96.4-96.7% and 97.6-98.8% in EM and 94.4-94.8% and 97.1-98% in Bayesian. There were no statistical differences between estimates. This finding indicates that the PCR assay could be useful screening tool for detecting heartworm antigen in dogs. This study was provided further evidences that Bayesian approach is an alternative approach to draw better inference about the performance of a new diagnostic test in case when either gold test is not available.

• Journal of Gifted/Talented Education
• /
• v.10 no.2
• /
• pp.25-46
• /
• 2000

These purposes are to have a necessity to be educated for the linguistic gifted among many gifted in speedy changeable age, and to find out what differences are of properties between the linguistic gifted children and nongifted children through comparing/analysing to gifted children any nongifted children using performance evaluation on writer's ability. Therefore, it intends to use as a assisting material in order to develop ability and properties of the linguistic gifted children and nongifted children as well. The studying details are 1) to compare/analyze thinking ability between the linguistic gifted children and nongifted children 2) to find out differences of thinking ability for unrealistic reasoning between the linguistic gifted children and nongifted children. The studying subjects had been chosen 3 children as a first grade in 'C' Gifted Academy and 3 children as a first grade in an elementary school from June 3, 1999 to June 12, 1999. The studying instrument was an evaluation of linguistic properties certification(Project Spectrum : Krechevsky,'1994). It had got a frequency calculation, average and standard deviation through the material anylzing with the program SPSSWIN. The conclusions are as belows, First, as a result of performance evaluation on writer's ability to gifted children and nongifted children, the gifted children were outstandingly shown the linguistic ability getting much higher score than nongifted children in respect of vocabulary level, structure of writing, and consistency/logicality of theme. Second, it was shown the gifted children had diffusing thought than nongifted children through the esthetic question and impformation memories with listening to the realistic juvenil story and the unrealistic juvenile story.

• Journal of Korean Elementary Science Education
• /
• v.43 no.2
• /
• pp.269-283
• /
• 2024

This study compared the characteristics of an experiment f or determining whether gas occupies space presented in elementary school science textbooks to examine the validity of the experiment, identify and improve problems in its presentation, and verify its effectiveness. This study interviewed third-year elementary school teachers who had experience teaching this experiment to students. Based on teachers' opinions and observations, this study identified issues with the current experiment, developed an improved experiment, and determined its effectiveness. Through this analysis, three key findings emerged. First, the study found that the original experiment on gases was presented in the same or highly similar manner in 5 of 7 textbooks (71.4%). Thus, while various textbooks have been developed with the aim of promoting diversity and creativity in scientific literature, most experiments presented in these books are identical. Second, the existing experiment was not suitable for its target audience (third-year elementary school students) and was difficult to observe directly. The interviewed teachers also deemed the validity of the experiment to be considerably low. Finally, the original experiment was improved; this improved version was determined to be highly valid, showing a statistically significant difference compared with the original experiment. The improved experiment was effective for students as it involved activities suitable for their intellectual level and was directly observable through the senses. Thus, the study analyzed and improved an existing science experiment f or elementary students, providing insights into the 2022 revised science authorized textbooks and implications for future textbook development.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.51 no.5
• /
• pp.466-476
• /
• 2006

The objective of this study was to compare and analyze the acceptability and consumption attitude for soy foods between Korean and Canadian university students as young consumers. This survey was carried out by questionnaire and the subjects were n=516 in Korea and n=502 in Canada. Opinions for soy foods in terms of general knowledge were that soy foods are healthy (86.5% in Korean and 53.4% in Canadian) or neutral (11.6% in Korean and 42.8% in Canadian), dairy foods can be substituted by soy foods (51.9% in Korean and 41.8% in Canadian), and soy foods are not only for vegetarians and milk allergy Patients but also for ordinary People (94.2% in Korean and 87.6% in Canadian). In main sources of information about soy foods, the rate by commercials on TV, radio or magazine was the highest (58.0%) for Korean students and the rate by family or friend was the highest(35.7%) for Canadian students. In consumption attitude, all of Korean students have purchased soy foods but only 55.4% of Canadian students have purchased soy foods, and soymilk was remarkably recognized and consumed then soy beverage and margarine in order. 76.4% of Korean students and 65.1% of Canadian students think soy foods are general and popular and can purchase easily, otherwise, in terms of price, soy foods were expensively recognized as 'more expensive than dairy foods' was 59.1% (Korean) and 54.7% (Canadian), and 'similar to dairy foods' was 36.8% (Korean) and 39.9% (Canadian). Major reasons for the rare consumption were 'I am not interested in soy foods' in Korean students (27.3%) and 'I prefer dairy foods to soy foods' in Canadian students (51.7%). However, consumption of soy foods in both countries are very positive and it will be increased.

• Journal of Intelligence and Information Systems
• /
• v.18 no.4
• /
• pp.43-57
• /
• 2012

To enhance the competitive advantage in a constantly changing business environment, an enterprise management must make the right decision in many business activities based on both internal and external information. Thus, providing accurate information plays a prominent role in management's decision making. Intuitively, historical data can provide a feasible estimate through the forecasting models. Therefore, if the service department can estimate the service quantity for the next period, the service department can then effectively control the inventory of service related resources such as human, parts, and other facilities. In addition, the production department can make load map for improving its product quality. Therefore, obtaining an accurate service forecast most likely appears to be critical to manufacturing companies. Numerous investigations addressing this problem have generally employed statistical methods, such as regression or autoregressive and moving average simulation. However, these methods are only efficient for data with are seasonal or cyclical. If the data are influenced by the special characteristics of product, they are not feasible. In our research, we propose a forecasting framework that predicts service demand of manufacturing organization by combining Case-based reasoning (CBR) and leveraging an unsupervised artificial neural network based clustering analysis (i.e., Self-Organizing Maps; SOM). We believe that this is one of the first attempts at applying unsupervised artificial neural network-based machine-learning techniques in the service forecasting domain. Our proposed approach has several appealing features : (1) We applied CBR and SOM in a new forecasting domain such as service demand forecasting. (2) We proposed our combined approach between CBR and SOM in order to overcome limitations of traditional statistical forecasting methods and We have developed a service forecasting tool based on the proposed approach using an unsupervised artificial neural network and Case-based reasoning. In this research, we conducted an empirical study on a real digital TV manufacturer (i.e., Company A). In addition, we have empirically evaluated the proposed approach and tool using real sales and service related data from digital TV manufacturer. In our empirical experiments, we intend to explore the performance of our proposed service forecasting framework when compared to the performances predicted by other two service forecasting methods; one is traditional CBR based forecasting model and the other is the existing service forecasting model used by Company A. We ran each service forecasting 144 times; each time, input data were randomly sampled for each service forecasting framework. To evaluate accuracy of forecasting results, we used Mean Absolute Percentage Error (MAPE) as primary performance measure in our experiments. We conducted one-way ANOVA test with the 144 measurements of MAPE for three different service forecasting approaches. For example, the F-ratio of MAPE for three different service forecasting approaches is 67.25 and the p-value is 0.000. This means that the difference between the MAPE of the three different service forecasting approaches is significant at the level of 0.000. Since there is a significant difference among the different service forecasting approaches, we conducted Tukey's HSD post hoc test to determine exactly which means of MAPE are significantly different from which other ones. In terms of MAPE, Tukey's HSD post hoc test grouped the three different service forecasting approaches into three different subsets in the following order: our proposed approach > traditional CBR-based service forecasting approach > the existing forecasting approach used by Company A. Consequently, our empirical experiments show that our proposed approach outperformed the traditional CBR based forecasting model and the existing service forecasting model used by Company A. The rest of this paper is organized as follows. Section 2 provides some research background information such as summary of CBR and SOM. Section 3 presents a hybrid service forecasting framework based on Case-based Reasoning and Self-Organizing Maps, while the empirical evaluation results are summarized in Section 4. Conclusion and future research directions are finally discussed in Section 5.