http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Lightweight Named Entity Extraction for Korean Short Message Service Text
( Choong-nyoung Seon ),( Jinhwan Yoo ),( Harksoo Kim ),( Ji-hwan Kim ),( Jungyun Seo ) 한국인터넷정보학회 2011 KSII Transactions on Internet and Information Syst Vol.5 No.3
In this paper, we propose a hybrid method of Machine Learning (ML) algorithm and a rule-based algorithm to implement a lightweight Named Entity (NE) extraction system for Korean SMS text. NE extraction from Korean SMS text is a challenging theme due to the resource limitation on a mobile phone, corruptions in input text, need for extension to include personal information stored in a mobile phone, and sparsity of training data. The proposed hybrid method retaining the advantages of statistical ML and rule-based algorithms provides fully-automated procedures for the combination of ML approaches and their correction rules using a threshold-based soft decision function. The proposed method is applied to Korean SMS texts to extract person`s names as well as location names which are key information in personal appointment management system. Our proposed system achieved 80.53% in F-measure in this domain, superior to those of the conventional ML approaches.
Kim, Choong-Nyoung,Choe, Byung-Don 한국경영과학회 1995 經營 科學 Vol.12 No.2
There have been two dominant paradigms in understanding and modeling an expert's decision-making behavior: output analysis and process-tracing. While the two paradigms are complementary, they have not been used yet in a combined manner. This study extends the previous research work in the two paradigms to inductive modeling research by 1) analyzing individual experts' decision strategies, 2) comparing performance of four popular inductive modeling methods, and 3) matching their performance against the type of decision strategy employed by experts.
중소기업에서 ASP(Application Service Provider) 서비스의 수용성과에 관한 연구
김충영 ( Choong Nyoung Kim ),김길래 ( Kil Lae Kim ) LGCNS 엔트루정보기술연구소 2006 Entrue Journal of Information Technology Vol.5 No.2
본 연구의 목적은 ASP 서비스의 활용성과에서 업종별 차이를 비교 분석하여, 활용되는 ASP 서비스의 유형과 업종에 따라 활용성과가 다르게 나타나는지를 분석하는 것이다. 이는 활용성과에 대한 연구에서 업종별 혹은 서비스 유형별 차이를 고려한 분석의 필요성을 제기하고 이들 요인이 ASP 서비스의 성과연구에서 새로운 변수로 추가될 수 있는지를 판단하기 위함이다. 또한 본 연구에서는 ASP 서비스의 활용성과에 영향을 미치는 요인을 파악하였다. 이를 토대로 ASP 서비스의 도입에 영향을 미치는 요인과 활용성과에 영향을 미치는 요인을 종합하여 ASP 서비스의 성과연구모형을 제시해 보았다. 본 연구의 분석 결과에 따르면, ASP의 활용성과는 사용하는 ASP 서비스의 유형에 따라 크게 차이가 있었다. 예를 들면, 제조업에서는 `내부효율성`이 두드러진 성과를 보인 반면 의료서비스업에서는 `외부협력`에서 가장 높은 성과를 나타냈다. `상거래`와 `외부협력`에서의 업종 간 차이는 통계적으로도 유의한 수준이었다. 이 결과는 각 업종에 따라 ASP의 활용용도(목적)가 다르기 때문에 다른 종류의 서비스를 사용하게 되고 따라서 활용성과에서도 차이를 보이는 것으로 해석할 수 있다. 또한 ASP 서비스의 활용성과에 영향을 미치는 요인에서도 그룹 간에 다른 형태를 보였다. 이는 향후 ASP 서비스의 활용성과에 대한 연구에서 중소기업의 규모와 업종, 그리고 사용되고 있는 ASP 서비스 유형 등이 주요 요인으로 고려되어야 할 필요가 있음을 시사하는 것이다. 본 연구에서 시도한 산업별 분석은 ASP 서비스를 사용하고 있거나 도입을 계획하는 중소기업들에게 구체적인 지침을 제공할 수 있을 뿐만 아니라 ASP 서비스의 활용성과를 극대화시키는데 도움을 줄 수 있으며 또한 ASP 서비스 공급자들의 전략수립에 도움을 줄 수 있을 것이다. The objective of this research is to explore organizational factors that influence on the performance of Application Service Provider(ASP) service for SME(Small & Medium Sized Enterprise). This research defines three domains of performance to be achieved through utilizing ASP services; 1) customer relationship & sales, 2) internal operational efficiency, and 3) data communication with exterior partners. This research also classifies ASP services into three types; Enterprise Service, Vertical Integration Service, and General Small Business Service. This classification of the ASP services is based on business type or objectives for adopting specific ASP services. The purpose of the classification is to demonstrate that the performance of ASP services should be related to the type of ASP services adopted by SME. The results of this study show that the internal operational efficiency was the most highly scored in the firms adopting Enterprise Services, while data communication was the most highly scored in the firms adopting Vertical Integration Services. The findings of this study suggest that such new factors as business type, business size, and the type of ASP services should be included for studying the performance of ASP services.
A Neural Network Approach to Compare Predictive Value of Accounting Versus Market Data
김충녕(Choong Nyoung Kim),전상경(Sang-gyung Jun),Kinsun Tam(Kinsun Tam) 한국지능정보시스템학회 2004 지능정보연구 Vol.10 No.1
This research compares the use of accounting data versus market data in the prediction of bankruptcy. Comparison is made through neural networks so that prediction accuracy is model-independent. Results of this study indicate that both market and accounting data provide useful information on corporate bankruptcies. Interestingly, using market and accounting information together can achieve substantial gain in prediction accuracy.
Review of Korean Speech Act Classification: Machine Learning Methods
Kim, Hark-Soo,Seon, Choong-Nyoung,Seo, Jung-Yun Korean Institute of Information Scientists and Eng 2011 Journal of Computing Science and Engineering Vol.5 No.4
To resolve ambiguities in speech act classification, various machine learning models have been proposed over the past 10 years. In this paper, we review these machine learning models and present the results of experimental comparison of three representative models, namely the decision tree, the support vector machine (SVM), and the maximum entropy model (MEM). In experiments with a goal-oriented dialogue corpus in the schedule management domain, we found that the MEM has lighter hardware requirements, whereas the SVM has better performance characteristics.
전문가 모델링에서 비선형모형과 선형모형 : 렌즈모형분석
김충녕 한국지능정보시스템학회 1995 지능정보연구 Vol.1 No.2
The field of human judgment and decision making provides useful methodologies for examining the human decision making process and substantive results. One of the methodologies is a lens model analysis which can examine valid nonlinearity in the human decision making process. Using this method, valid nonlinearity in human decision behavior can be successfully detected. Two linear (statistical) models of human experts and two nonlinear models of human experts are compared in terms of predictive accuracy (predictive validity). The results indicate that nonlinear models can capture factors (valid nonlinearity) that contribute to the experts' predictive accuracy, but not factors (inconsistency) that detract from their predictive accuracy. Then, it is argued that nonlinear models can be more accurate than linear models, or as accurate as human experts, especially when human experts employ valid nonlinear strategies in decision making.
Review of Korean Speech Act Classification
Harksoo Kim,Choong-Nyoung Seon,Jungyun Seo 한국정보과학회 2011 Journal of Computing Science and Engineering Vol.5 No.4
To resolve ambiguities in speech act classification, various machine learning models have been proposed over the past 10 years. In this paper, we review these machine learning models and present the results of experimental comparison of three representative models, namely the decision tree, the support vector machine (SVM), and the maximum entropy model (MEM). In experiments with a goal-oriented dialogue corpus in the schedule management domain, we found that the MEM has lighter hardware requirements, whereas the SVM has better performance characteristics.