• 전자공학회논문지B
• /
• 제31B권5호
• /
• pp.134-140
• /
• 1994

In this paper, an algorithm of CBAM(Combination Bidirectional Associative Memory) model proposes, analyzes and tests CBAM model `s performancess by simulating with recalls and recognitions of patterns. In learning-procedure each correlation matrix of training patterns is obtained. As each correlation matrix's some elements correspond to juxtaposition, all correlation matrices are merged into one matrix (Combination Correlation Matrix, CCM). In recall-procedure, CCM is decomposed into a number of correlation matrices by spiliting its elements into the number of elements corresponding to all training patterns. Recalled patterns are obtained by multiplying input pattern with all correlation matrices and selecting a pattern which has the smallest value of energy function. By using a CBAM model, we have some advantages. First, all pattern having less than 20% of noise can be recalled. Second, memory capacity of CBAM model, can be further increased to include English alphabets or patterns. Third, learning time of CBAM model can be reduced greatly because of operation to make CCM.

• 정보교육학회논문지
• /
• 제1권2호
• /
• pp.45-56
• /
• 1997

A design of Advisory Tutoring Agent(ATA) is proposed to help a student on the basis of a student-oriented discovery learning, The agents adaptively build a student model and interact with a student as well as each other to give a piece of advice at a proper time. The appropriateness of advice depends on the agents' reasoning sod interaction performed based on the student model. domain knowledge, teaching strategy, and user-friendly interface. The design has been applied to a simple English learning environment.

• 스마트미디어저널
• /
• 제5권2호
• /
• pp.24-32
• /
• 2016

Recently, the development of electronic teaching materials and the demand of digital learners have led the needs on the education contents that replace learning from character information and the change of an information design method for this. Chinese character education in the traditional schooling mainly focuses on writing and memorization (semantic memory). This way that the stories do not exist has brought the learners' recognition that Chinese character is difficult to learn. Meanwhile, for a language study such as English, cross-media development between printed materials and audio-visual materials has been actively introduced. The method that extends episode memories along with memorization through a story is widely used. Therefore, this content suggests a prototype, which is broken away from an existing way of learning Chinese character that mainly focuses on writing, one sided instruction and information cramming. This makes learners learn through a story from printed materials and animation. Furthermore, it suggests a method that extends episode memories through Chinese education contents based on IoT explaining the principle of Chinese character by combining IT technology (information and communications, IoT) and education contents on block toys.

• International Journal of Computer Science & Network Security
• /
• 제21권9호
• /
• pp.155-162
• /
• 2021

The expansion of the world wide web has led to a huge amount of user generated content over different forums and social media platforms, these rich data resources offer the opportunity to reflect, and track changing public sentiments and help to develop proactive reactions strategies for decision and policy makers. Analysis of public emotions and opinions towards events and sentimental trends can help to address unforeseen areas of public concerns. The need of developing systems to analyze these sentiments and the topics behind them has emerged tremendously. While most existing works reported in the literature have been carried out in English, this paper, in contrast, aims to review recent research works in Arabic language in the field of thematic sentiment analysis and which techniques they have utilized to accomplish this task. The findings show that the prevailing techniques in Arabic topic-based sentiment analysis are based on traditional approaches and machine learning methods. In addition, it has been found that considerably limited recent studies have utilized deep learning approaches to build high performance models.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2019년도 제31회 한글 및 한국어 정보처리 학술대회
• /
• pp.236-238
• /
• 2019

신경망 기계 번역(Neural Machine Translation)은 주로 지도 학습(Supervised learning)을 이용한 End-to-end 방식의 연구가 이루어지고 있다. 그러나 지도 학습 방법은 데이터가 부족한 경우에는 낮은 성능을 보이기 때문에 BERT와 같은 대량의 단일 언어 데이터로 사전학습(Pre-training)을 한 후에 미세조정(Finetuning)을 하는 Transfer learning 방법이 자연어 처리 분야에서 주로 연구되고 있다. 최근에 발표된 MASS 모델은 언어 생성 작업을 위한 사전학습 방법을 통해 기계 번역과 문서 요약에서 높은 성능을 보였다. 본 논문에서는 영어-한국어 기계 번역 성능 향상을 위해 MASS 모델을 신경망 기계 번역에 적용하였다. 실험 결과 MASS 모델을 이용한 영어-한국어 기계 번역 모델의 성능이 기존 모델들보다 좋은 성능을 보였다.

• ETRI Journal
• /
• 제46권1호
• /
• pp.48-58
• /
• 2024

This paper presents the development of language tutoring systems for nonnative speakers by leveraging advanced end-to-end automatic speech recognition (ASR) and proficiency evaluation. Given the frequent errors in non-native speech, high-performance spontaneous speech recognition must be applied. Our systems accurately evaluate pronunciation and speaking fluency and provide feedback on errors by relying on precise transcriptions. End-to-end ASR is implemented and enhanced by using diverse non-native speaker speech data for model training. For performance enhancement, we combine semisupervised and transfer learning techniques using labeled and unlabeled speech data. Automatic proficiency evaluation is performed by a model trained to maximize the statistical correlation between the fluency score manually determined by a human expert and a calculated fluency score. We developed an English tutoring system for Korean elementary students called EBS AI Peng-Talk and a Korean tutoring system for foreigners called KSI Korean AI Tutor. Both systems were deployed by South Korean government agencies.

• 한국융합학회논문지
• /
• 제7권1호
• /
• pp.145-153
• /
• 2016

연구는 D대학에 재학 중인 4개학과(유아교육학과, 아동영어교육학과, 언어치료학과, 한국어교원학과 학생) 소속 총 300명을 대상으로 사상체질에 따른 학습스타일과 전공에 따른 학습스타일 및 좌뇌 및 우뇌의 우세성을 살펴보아 대학생의 체질에 맞는 학습스타일과 전공에 적합한 학습스타일을 제안하기 위해 실시하였다. 연구결과 사상체질에 따른 학습스타일에서 내향형과 외향형에서 유의한 차이가 나타났다. 소양인은 외향적 학습스타일을 지닌 사람이 많은 반면에 소음인은 내향적 학습스타일을 가지고 있는 것으로 나타났다. 전공에 따른 학습스타일에 있어서는 신체형에서만 유의한 차이가 나타났다. 좌뇌와 우뇌의 우세성을 전공에 따른 차이를 살펴보았을 때 일부 문항에서만 유의한 차이가 나타났다. 이와 같은 결과는 대학에서 학습자나 학과 특성을 고려하지 않는 획일적 강의식 방법보다는 학습자의 체질 특성과 학과의 특성을 반영한 교수-학습방법을 개발해야 한다는 것에 의의를 둔다.

• 한국정보시스템학회지:정보시스템연구
• /
• 제28권4호
• /
• pp.293-311
• /
• 2019

목적 본 연구는 2011년부터 8년간의 영문문헌에 대해 메타분석법을 이용하여 소셜미디어의 사용과 학습성과간의 관계를 규명하고자 하였다. 또한 소셜미디어 사용 상황과 연구분석방법론 변인의 조절효과 여부를 분석하였다. 연구방법론 주요 연구방법으로 유사한 연구 의문점이 제시된 선행의 실증연구들에 대해 메타분석기법을 사용하였으며, 문헌분석을 통해 정량적 데이터를 도출하고, 이를 실증 분석하였다. 연구결과 연구결과로 소셜미디어의 사용과 학습성과간에는 정의 상관을 보였으며, 상황변수와 연구방법론 변수가 조절효과를 보였다. 상황변수의 구성개념으로는 소셜미디어형태, 사용자 집단, 플랫폼 종류 등으로 하였고, 분석을 위한 측정방법 변수에는 측정모형, 데이터속성 등의 개념으로 구성하였다.

• International Journal of Advanced Culture Technology
• /
• 제1권2호
• /
• pp.24-32
• /
• 2013

This paper determined students' ranks of difficulty on the use of materials in terms of 1) understanding the layout of the learning materials, 2) reading comprehension of the learning materials, and 3) realization on relevance to needs of the learning materials. It also determined students' 4) rank and frequency of attitude on the materials. With the data gathered through 128 survey questionnaires, 7 focused group discussions, and 10 interviews, the results were found out that there was an inappropriate assessment procedure set by this particular university. The researcher concludes that: 1) design of four types of classes by just using the two textbooks with their respective workbooks is grammar-based with limited conversation activities; 2) placement for these students in one big class size was implemented without considering their common interest and motivation and language levels; and, 3) qualification of teachers teaching these EFL students did not support students' real needs and the language program itself. Content professors who were made to teach may have the ability to input learning, but their teaching styles may differ from the ones who are real English teachers. This paper then recommends that teachers and school administration should have an appropriate placement exam before students attend the class, especially in a big class size. There could only be a few problems among students in one big class size when students' level of competence is proportioned. With this, topics and conversation activities can even be more flexible with the maneuver of art of questioning, various dimensions of thinking, strategic competence, learning attitude or behavior, etc. to ensure sustenance of communicative mode and level of interest and motivation in the classroom. Grammar-based instruction can only be taught when a need arises. Thus, the course description of each class will be able to transact the objectives ready for developing students' communication competence. Moreover, proper measurement can be utilized to validly assess the amount of students' learning and the progress of language curriculum design in terms of materials selection and teaching approach.

• 디지털융복합연구
• /
• 제17권9호
• /
• pp.173-184
• /
• 2019

본 연구는 대학교육 시스템 내에서 MOOC을 활용한 플립 러닝 적용의 효과를 알아보기 위해 수행되었다. 이를 위해 총 여섯 명의 대학생들이 10주 동안의 새로운 학습 경험에 참여하였다. 참여자들은 먼저 MOOC 웹사이트에서 제공되는 학습 내용을 통해 온라인 활동을 수행하고, 오프라인 강의실에서 이와 연계된 참여적 학습을 수행하였다. 수업이 종료된 이후 연구참여자들을 대상으로 반구조화된 대면 인터뷰가 시행되었다. 연구결과 이 교수 방법은 학습자들이 높은 동기수준을 갖고 학습활동을 수행한 것으로 나타났다. 그러나 외국어로 제공되는 학습콘텐츠로 인한 학습제약, 새로운 학습방법에 대한 문화적 부적응의 문제들이 발견되었다. 본 연구를 바탕으로 향후 발전방안이 논의되었다.