• Title/Summary/Keyword: Document Analysis

Search Result 81, Processing Time 0.123 seconds

Deep Learning Document Analysis System Based on Keyword Frequency and Section Centrality Analysis

  • Lee, Jongwon;Wu, Guanchen;Jung, Hoekyung
    • Journal of information and communication convergence engineering
    • /
    • v.19 no.1
    • /
    • pp.48-53
    • /
    • 2021
  • Herein, we propose a document analysis system that analyzes papers or reports transformed into XML(Extensible Markup Language) format. It reads the document specified by the user, extracts keywords from the document, and compares the frequency of keywords to extract the top-three keywords. It maintains the order of the paragraphs containing the keywords and removes duplicated paragraphs. The frequency of the top-three keywords in the extracted paragraphs is re-verified, and the paragraphs are partitioned into 10 sections. Subsequently, the importance of the relevant areas is calculated and compared. By notifying the user of areas with the highest frequency and areas with higher importance than the average frequency, the user can read only the main content without reading all the contents. In addition, the number of paragraphs extracted through the deep learning model and the number of paragraphs in a section of high importance are predicted.

Keyword Weight based Paragraph Extraction Algorithm (문단 가중치 분석 기반 본문 영역 선정 알고리즘)

  • Lee, Jongwon;Yu, Seongjong;Kim, Doan;Jung, Hoekyung
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2018.05a
    • /
    • pp.462-463
    • /
    • 2018
  • Traditional document analysis systems used word-based analysis using a morphological analyzer or TF-IDF technique. These systems have the advantage of being able to derive key keywords by calculating the weights of the keywords. On the other hand, it is not appropriate to analyze the contents of documents due to the structural limitations. To solve this problem, the proposed algorithm calculates the weights of the documents in the document and divides the paragraphs into areas. And we calculate the importance of the divided regions and let the user know the area with the most important paragraphs in the document. So, it is expected that the user will be provided with a service suitable for analyzing documents rather than using existing document analysis systems.

  • PDF

Document Analysis based Main Requisite Extraction System (문서 분석 기반 주요 요소 추출 시스템)

  • Lee, Jongwon;Yeo, Ilyeon;Jung, Hoekyung
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.23 no.4
    • /
    • pp.401-406
    • /
    • 2019
  • In this paper, we propose a system for analyzing documents in XML format and in reports. The system extracts the paper or reports of keywords, shows them to the user, and then extracts the paragraphs containing the keywords by inputting the keywords that the user wants to search within the document. The system checks the frequency of keywords entered by the user, calculates weights, and removes paragraphs containing only keywords with the lowest weight. Also, we divide the refined paragraphs into 10 regions, calculate the importance of the paragraphs per region, compare the importance of each region, and inform the user of the main region having the highest importance. With these features, the proposed system can provide the main paragraphs with higher compression ratio than analyzing the papers or reports using the existing document analysis system. This will reduce the time required to understand the document.

A Study on the Concept and Characteristics of Heritage Impact Assessments for Cultural World Heritage Properties - Focused on ICOMOS Guidance on Heritage Impact Assessments and Case Reports - (유산영향평가의 개념과 특성에 관한 연구 - 이코모스 유산영향평가 지침서와 사례 보고서를 중심으로 -)

  • Kim, Chung Ho;Lee, Kyung-Ah;Kim, Dong Min
    • Journal of the Architectural Institute of Korea
    • /
    • v.36 no.8
    • /
    • pp.61-72
    • /
    • 2020
  • This study aims to identify the concept and characteristics of Heritage Impact Assessments (HIA) in order to introduce and implement HIA in Korea. For this, the 2011 ICOMOS guidance on HIA and case reports were analyzed through the methods of document analysis and case study. As a result, the study reached the following five conclusions: First, HIA is an assessment system based on Outstanding Universal Value (OUV), using specific assessment items and methods drawn from each property and its proposed development. Second, HIA team as transparent and independent assessment agent has the authority to plan, conduct, and take the responsibility for HIA. Third, HIA assessment methods are derived and developed through consultation with relevant stakeholders. Fourth, HIA procedure consists two main stages such as scoping stage creating the scoping report and undertaking stage producing the HIA report. Fifth, mitigative measures and recommendations are proposed in order to avoid, reduce, and mitigate negative impacts of potential developments on OUV of properties. Finally, the study is expected to promote academic understanding and vibrant discussions for domestic introduction and smooth implementation of HIA.

The History and Characteristics of Korean Traditional Ondol(Gudle) studied through Document Analysis (문헌에 의해 분석된 한국 전통 온돌(구들)의 역사와 특성)

  • Kim, June Bong;Jeong, Sang Kyu
    • KIEAE Journal
    • /
    • v.8 no.6
    • /
    • pp.3-10
    • /
    • 2008
  • Since fire was founded in the world, human races have invented various heating methods. Ondol is traditional heating method in Korea. It is very the important work to trace the history and characteristics of Ondol which originated and was developed in the Korean peninsula. Especially, the study on Ondol will contribute to improving the present heating methods and predicting future ones. In this paper, we shall study through the analysis of documents such as oriental documents, the document of Choseon dynasty, European documents and American documents. In order to discover the origins of Ondol as one of the excellent heating method all over the world, This study aims at identifying the history and characteristics of Ondol in the Korean peninsula, through document analysis. Results of this study are as follows. 1) The first document about Ondol is Sookyongjoo(水經注), Chinese ancient geography book. Contents recorded in the book include the description related to Ondol at Kwankyesa temple which was located at the border land between Gogooryo(ancient Korea) and the northeast of China. 2) Ondol was popular heating method in Gogooryo(ancient Korea) and it was used in not only Gogooryo but also Silla Kingdom and Beakje Kingdom. Thereafter, it was also used widely in Goryo dynasty and Choseon dynasty. Thereby we know that Ondol has been used as a heating method for a long time in the Korean peninsula. 3) Ondol was covered with a floor paper since the beginning of Choseon dynasty. the paper made room clean and impacted on Korean life style. Because the floor was clean and warm, Koreans thus took off shoes and sat on the floor. 4) Ondol was spreaded to Jeju island in Korea before 16th century but wasn't used widely there. The reason was that Ondol was rare high class heating system and the weather was warm in Jeju island. 5) The overspreading of Ondol caused that poor people built roughly Ondol in the last of Choseon dynasty. So, the quality of Ondol gradually became lower and lower. 6) A westerner was impressed by the novelty of Ondol and Frank Lloyd Wright had played an important role to update and spread Ondol widely all over the world. Hailing Ondol as the ideal heating system, Frank Lloyd Wright began incorporating it in his buildings back in the U.S. and even invented a modified ondol system, using hot water running through pipes instead of the hot exhaust through flues.

Web Document Analysis based Personal Information Hazard Classification System (웹 문서 분석 기반 개인정보 위험도 분류 시스템)

  • Lee, Hyoungseon;Lim, Jaedon;Jung, Hoekyung
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.22 no.1
    • /
    • pp.69-74
    • /
    • 2018
  • Recently, personal information leakage has caused phishing and spam. Previously developed systems focus on preventing personal information leakage. Therefore, there is a problem that the leakage of personal information can not be discriminated if there is already leaked personal information. In this paper, we propose a personal information hazard classification system based on web document analysis that calculates the hazard. The system collects web documents from the Twitter server and checks whether there are any user-entered search terms in the web documents. And we calculate the hazard classification weighting of the personal information leaked in the web documents and confirm the authority of the Twitter account that distributed the personal information. Based on this, the hazard can be derived and the user can be informed of the leakage of personal information of the web document.

Examining the Current State of Research on Mathematics Curriculum (수학과 교육과정연구 분석 및 고찰)

  • Kim, Goo-Yeon;Kwon, Na-Young;Kim, Rae-Young
    • Journal of the Korean School Mathematics Society
    • /
    • v.15 no.2
    • /
    • pp.317-330
    • /
    • 2012
  • The purpose of this paper is to examine current state of curriculum research and research methods used in the research in Korea. Results from the review of peer-reviewed research articles suggest that the ways in which the research studies on curriculum in Korea sorted out issues seemed to heavily concentrate on the written and intended curriculum by means of a document analysis. The topics of curriculum studies were biased in the studies of intended curriculum, and a significant number of curriculum studies were related to elementary levels. Regarding the research methods, the findings showed that many studies on mathematics curriculum have focused on national curriculum, textbooks, and curriculum materials, document analysis are the most frequently used methods in the studies of mathematics curriculum. We finally suggest pursuing various research topics and issues on curriculum, balancing weigh on the written and enacted curriculum, and deeper analysis and investigation of textbooks.

  • PDF

A Case Study of Two Korean Students' Classroom Interactions in a Graduate Course in America

  • Nam, Jung-Mi
    • English Language & Literature Teaching
    • /
    • v.13 no.3
    • /
    • pp.57-75
    • /
    • 2007
  • This small-scale research project attempts to describe and explore the Korean students' perspectives on oral classroom interaction in a second language classroom in a graduate course in America. Based on the interpretist paradigm, this study employed the qualitative research methodology, triangulating the following methods: class observation, interviews, and document analysis. The findings are that the Korean participants perceived the importance of oral classroom interaction in an American classroom, and that there were shared several factors which influence their participation such as socio-cultural differences, course content, English skills, course requirement, and classroom activity types. Based upon the findings, pedagogical implications are provided for the teachers to help Korean students achieve academic success in American universities.

  • PDF

Deep-Learning Approach for Text Detection Using Fully Convolutional Networks

  • Tung, Trieu Son;Lee, Gueesang
    • International Journal of Contents
    • /
    • v.14 no.1
    • /
    • pp.1-6
    • /
    • 2018
  • Text, as one of the most influential inventions of humanity, has played an important role in human life since ancient times. The rich and precise information embodied in text is very useful in a wide range of vision-based applications such as the text data extracted from images that can provide information for automatic annotation, indexing, language translation, and the assistance systems for impaired persons. Therefore, natural-scene text detection with active research topics regarding computer vision and document analysis is very important. Previous methods have poor performances due to numerous false-positive and true-negative regions. In this paper, a fully-convolutional-network (FCN)-based method that uses supervised architecture is used to localize textual regions. The model was trained directly using images wherein pixel values were used as inputs and binary ground truth was used as label. The method was evaluated using ICDAR-2013 dataset and proved to be comparable to other feature-based methods. It could expedite research on text detection using deep-learning based approach in the future.

Reflections in Peer Evaluation: Is the Attended Teacher Training Program the Implemented Training program?

  • Delice, Ali;Sevimli, Eyup;Aydin, Emin
    • Research in Mathematical Education
    • /
    • v.13 no.2
    • /
    • pp.141-150
    • /
    • 2009
  • This study gives opportunity for investigating how student teachers view the teaching profession and how they transfer their pedagogical knowledge into practice. The aim of the study is to investigate the teaching skills student teachers gained in the assessment of micro teaching of their peers. The participants are 30 mathematics student teachers enrolled in the teacher training program in a state university. Document analysis and semi-structured interviews are the research instruments and inferential & descriptive statistics are used for the data analysis. The findings suggest that the qualitative and quantitative peer assessments of student teachers were graded differently which results from the difference of perceptions about teaching and different conceptualizations of the teaching qualifications.

  • PDF