• Annual Conference of KIPS
• /
• 2002.04a
• /
• pp.179-182
• /
• 2002

웹을 저작 공간으로 사용한 Wiki Wiki Web[4]은 텍스트 자원을 사용한 복잡하고 다양한 이야기의 표현이 가능하며 실시간은 아니지만 시분할 방식의 이야기 공동 저작과 감상을 지원한다. 하지만 이러한 도구를 사용하여 그림일기와 같은 그림과 텍스트 내공이 복합된 이야기를 저작하는 경우, 저작자는 텍스트 자원을 사용하여 이야기를 구성해야 하기 때문에 그림이 표현되어야 하는 부분을 표현할 수 없으며 공동저작을 손쉽게 하는 자동화 도구를 제공하지 않기 때문에 저작도구의 사용에 대한 불편함을 느끼게 된다. 이처럼 그림일기나 동화 등의 다양한 형태의 이야기를 표현하기 위해서 사용자가 멀티미디어 자원들을 사용하도록 하고 손쉬운 이야기를 구성하도록 하는 디지털 스토리텔링 저작도구가 요구된다. 본 논문에서는 저작자가 온라인상에서 직접 그린 스케치 영상을 사용하여 이야기의 배경과 캐릭터를 만들고 그것을 이야기 저작 소재로 사용하도록 하는 배경 및 액터 생성도구를 제공하고 다양한 형태의 이야기를 저작자가 손쉽게 표현하도록 하는 이야기 구성의 자동화 도구를 제공하면서 여러 사용자들이 실시간으로 이야기 저작과 감상에 공동으로 참여하도록 하여 저작된 결과를 애니메이션으로 감상할 수 있도록 하는 디지털 스토리텔링 도구를 설계하고 구현하였다.

• Journal of the Korean Society for information Management
• /
• v.6 no.1
• /
• pp.93-117
• /
• 1989

The objective of this study is to design an automatic abstracting system through the analysis of natural language texts. For this purpose a knowledge-based system operating on the basis of domain knowledge was developed. The procedure of generating an abstract consists of three steps: (1) A knowledge-base containing domain knowledge necessary to understand a text is constructed using frame and semantic network structures,and preliminary abstracts are prepared for various cases. (2) Input text is analysed on the basis of domain knowledge in order to extract information filling slots of the abstract with. (3) A Preliminary abstract corresponding to the input text is called and filled with the information, completing the abstract.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.9
• /
• pp.1135-1143
• /
• 2021

Recently, text collection using a web crawler for big data analysis has been frequently performed. However, in order to collect only the necessary text from a web page that is complexly composed of numerous tags and texts, there is a cumbersome requirement to specify HTML tags and style attributes that contain the text required for big data analysis in the web crawler. In this paper, we proposed a method of extracting text using the frequency of text appearing in web pages without specifying HTML tags and style attributes. In the proposed method, the text was extracted from the DOM tree of all collected web pages, the frequency of appearance of the text was analyzed, and the main text was extracted by excluding the text with high frequency of appearance. Through this study, the superiority of the proposed method was verified.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.2
• /
• pp.427-436
• /
• 2021

The purpose of this study is to implement a machine learning language model that learns literary texts. Literary texts have an important characteristic that pairs of question-and-answer are not frequently clearly distinguished. Also, literary texts consist of pronouns, figurative expressions, soliloquies, etc. They hinder the necessity of machine learning using literary texts by making it difficult to learn algorithms. Algorithms that learn literary texts can show more human-friendly interactions than algorithms that learn general sentences. For this goal, this paper proposes three text correction tasks that must be preceded in researches using literary texts for machine learning language model: pronoun processing, dialogue pair expansion, and data amplification. Learning data for artificial intelligence should have clear meanings to facilitate machine learning and to ensure high effectiveness. The introduction of special genres of texts such as literature into natural language processing research is expected not only to expand the learning area of machine learning, but to show a new language learning method.

• Journal of IKEEE
• /
• v.24 no.4
• /
• pp.1086-1092
• /
• 2020

An autonomous agent for real world should be able to recognize text in scenes. With the advancement of deep learning, various DNN models have been utilized for transformation, feature extraction, and predictions. However, the existing state-of-the art STR (Scene Text Recognition) engines do not achieve the performance required for real world applications. In this paper, we introduce a performance-improvement method through an add-on composed of an OCR (Optical Character Recognition) engine and a classifier for STR engines. On instances from IC13 and IC15 datasets which a STR engine failed to recognize, our method recognizes 10.92% of unrecognized characters.

• The Journal of Society for e-Business Studies
• /
• v.19 no.3
• /
• pp.107-123
• /
• 2014

Current text mining techniques suffer from the problem that the conventional text representation models cannot express the semantic or conceptual information for the textual documents written with natural languages. The conventional text models represent the textual documents as bag of words, which include vector space model, Boolean model, statistical model, and tensor space model. These models express documents only with the term literals for indexing and the frequency-based weights for their corresponding terms; that is, they ignore semantical information, sequential order information, and structural information of terms. Most of the text mining techniques have been developed assuming that the given documents are represented as 'bag-of-words' based text models. However, currently, confronting the big data era, a new paradigm of text representation model is required which can analyse huge amounts of textual documents more precisely. Our text model regards the 'concept' as an independent space equated with the 'term' and 'document' spaces used in the vector space model, and it expresses the relatedness among the three spaces. To develop the concept space, we use Wikipedia data, each of which defines a single concept. Consequently, a document collection is represented as a 3-order tensor with semantic information, and then the proposed model is called text cuboid model in our paper. Through experiments using the popular 20NewsGroup document corpus, we prove the superiority of the proposed text model in terms of document clustering and concept clustering.

• Journal of The Korean Association of Information Education
• /
• v.23 no.6
• /
• pp.543-550
• /
• 2019

In 2006, Janet Wing defined computational thinking and operated SW education as a formal curriculum in the UK in 2013. This study collected related research papers by using computational thinking, which has recently increased in importance, and analyzed it using text mining. In the first, CONCOR analysis was conducted with the keyword of computational thinking. In the second, text mining of the components of computational thinking was selected by the repr23esentative academic journals at domestic and foreign. As a result of the two-time analysis, first, abstraction, algorithm, data processing, problem decomposition, and pattern recognition were the core of the study of computational thinking component. Second, research on convergence education centered on computational thinking and science and mathematics subjects was actively conducted. Third, research on computational thinking has been expanding since 2010. Research and development of the classification and definition of computational thinking and components and applying them to education sites should be conducted steadily.

• Journal of vocational education research
• /
• v.33 no.3
• /
• pp.83-104
• /
• 2014

The study examined the trends of research on Meister high schools in Korea. The study also investigated differences of research interests between the university faculty and graduate students who are the future researchers in this field. A total of 56 research articles were analyzed using the network text analysis method and the content analysis. The results showed that 56% of all studies was done to reveal the distinguishable characteristics of Meister students and teachers compared to their counterpart in vocational schools. 17.6% of studies were about school curriculum, while 14.0% of studies were on school organization and operation. Only 12.3% of studies were conducted to evaluate school performance. Quantitative studies outnumbered qualitative ones. Based on the results, this study suggested implications for policies and future research on meister high school.

• Korean Journal of Child Education & Care
• /
• v.19 no.3
• /
• pp.157-170
• /
• 2019

Objective: The purpose of the study was to investigate the current status of early childhood teachers' picture book reading activities and their knowledge and utilization of the picture book peritexts. Methods: The subjects were 276 early childhood teachers in Seoul metropolitan area. The survey was conducted to investigate early childhood teachers' current status of picture book reading activities as well as their knowledge and utilization of picture book peritexts. The collected data were analyzed using SPSS Statistics 21.0 program to analyze descriptive statistics such as frequency and percentage. Results: As results, most early childhood teachers recognized that reading picture books to young children was very important and responded that the purpose of reading picture books was to develop children's imagination and creativity. In terms of early childhood teachers' knowledge on 12 peritexts, some peritexts such as 'title', 'cover' and 'title page' were recognized at high level but other peritexts such as typography and layout were at low level. In addition, early childhood teachers' utilization level of peritexts were shown as relatively low compared to their knowledge level. Conclusion/Implications: The study results imply that early childhood teachers need to be informed of the concepts of picture book peritexts and encouraged to utilize peritexts while reading picture books to young children.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1994.06c
• /
• pp.235-240
• /
• 1994

모음 검출을 통하여 미리 등록한 단어가 아닌 경우에도 화자를 인식할 수 있도록 특징 파라메터를 개발하고, 실용화가 가능하도록 처리 방법을 간략화한 텍스트 독립 화자 인식 연구를 진행하였다. 이를 위해서, 화자가 발성한 음성에서 모음을 검출하여 화자인식에 사용하는 방법을 제안하였으며, 인식은 각 화자가 발성한 음성 신호에서 모음을 검출한 다음, 검출된 모음의 29 채널의 주파수 에너지를 퍼지값으로 효현한 후, 퍼지 추론을 적용하여 수행하였다. 실험을 위해 모음 검출 알고리듬을 개발하였으며, 화자인식의 특징 파라메터로 29 채널 주파수 에너지를 제안하였는데, 별도의 코드북 없이 사용이 가능하고, 기존의 파라메터에 비해 인식율이 높으면서도 구성 및 계산이 간단한 특징이 있다. 실험결과, 미리 작성된 표준패턴과 동일한 단어를 사용한 텍스트 의존 화자 인식 실험은 95.5% 인식율을 보였고, 표준 패턴과 다른 종류의 단어를 사용한 텍스트 독립 화자인식 실험은 94.2% 인식율을 보이고 있다.