• 제목/요약/키워드: text difficulty

검색결과 138건 처리시간 0.026초

전문데이터베이스의 탐색특성에 관한 연구 - 주제전문가와 탐색전문가 - (A Study of the Behaviours in Searching Full-Text Databases- Subject Specialists vs. Professional Searchers -)

  • 이응봉
    • 한국문헌정보학회지
    • /
    • 제30권2호
    • /
    • pp.51-86
    • /
    • 1996
  • 본 연구는 전문데이터베이스의 탐색에 있어서 주제전문가와 탐색전문가는 어떠한 특징적인 차이가 있는지를 밝히려 하였다. 이 연구를 통하여 얻어진 결론을 요약하면, 주제전문가와 탐색전문가는 전문데이터베이스의 탐색에, 있어서 탐색질문의 분석(탐색질문의 이해도. 탐색어 선정의 난이도, 탐색결과에 대한 기대수준), 탐색과정(탐색어수, 연산자 순 브라우징 문헌 순 접속시긴 출력문헌 건당 소요시긴 적합문헌 건당 소요시간), 탐색결과 (적합문헌수 재현율 정확율, 총 탐색비용 출력문헌 건당 소요비용, 적합문헌 건당 소요비용, 탐색결과에 대한 만족도)에 대하여 뚜렷한 차이를 나타내는 것으로 밝혀졌다.

  • PDF

빅데이터 분석 기반의 오피니언 마이닝을 이용한 정보화 사업 평가 분석 (An Analysis of IT Proposal Evaluation Results using Big Data-based Opinion Mining)

  • 김홍삼;김종수
    • 산업경영시스템학회지
    • /
    • 제41권1호
    • /
    • pp.1-10
    • /
    • 2018
  • Current evaluation practices for IT projects suffer from several problems, which include the difficulty of self-explanation for the evaluation results and the improperly scaled scoring system. This study aims to develop a methodology of opinion mining to extract key factors for the causal relationship analysis and to assess the feasibility of quantifying evaluation scores from text comments using opinion mining based on big data analysis. The research has been performed on the domain of publicly procured IT proposal evaluations, which are managed by the National Procurement Service. Around 10,000 sets of comments and evaluation scores have been gathered, most of which are in the form of digital data but some in paper documents. Thus, more refined form of text has been prepared using various tools. From them, keywords for factors and polarity indicators have been extracted, and experts on this domain have selected some of them as the key factors and indicators. Also, those keywords have been grouped into into dimensions. Causal relationship between keyword or dimension factors and evaluation scores were analyzed based on the two research models-a keyword-based model and a dimension-based model, using the correlation analysis and the regression analysis. The results show that keyword factors such as planning, strategy, technology and PM mostly affects the evaluation result and that the keywords are more appropriate forms of factors for causal relationship analysis than the dimensions. Also, it can be asserted from the analysis that evaluation scores can be composed or calculated from the unstructured text comments using opinion mining, when a comprehensive dictionary of polarity for Korean language can be provided. This study may contribute to the area of big data-based evaluation methodology and opinion mining for IT proposal evaluation, leading to a more reliable and effective IT proposal evaluation method.

대어휘 연속음성 인식을 위한 결합형태소 자동생성 (Automatic Generation of Concatenate Morphemes for Korean LVCSR)

  • 박영희;정민화
    • 한국음향학회지
    • /
    • 제21권4호
    • /
    • pp.407-414
    • /
    • 2002
  • 본 논문에서는 형태소를 인식 단위로 하는 한국어 연속음성 인식의 성능 개선을 위해 결합형태소를 자동으로 생성하는 방법을 제시한다. 학습코퍼스의 54%를 차지하고 오인식의 주요인이 되는 단음절 형태소를 감소시켜서 인식 성능을 높이는 것을 목적으로 한다. 품사의 접속 규칙을 이용한 기존의 지식기반의 형태소 결합방법은 접속 규칙의 생성이 어렵고, 학습 코퍼스에 나타난 출현 빈도를 반영하지 못하여 저빈도 결합형태소를 다수 생성하는 경향을 보였다. 본 논문에서 제시하는 방법은 학습데이터의 통계정보를 이용하여 결합형태소를 자동 생성한다. 결합할 형태소 쌍 선정을 위한 평가척도로는 형태소 쌍의 빈도, 상호정보, 유니그램 로그 유도값(unigram log likelihood)을 이용하였고 여기에 한국어의 특성 반영을 위해 단음절 형태소 제약과 형태소 결합길이를 제한하는 두개의 제약사항을 추가하였다. 학습에 사용된 텍스트 코퍼스는 방송뉴스와 신문으로 구성된 7백만 형태소이고, 최빈도 2만 형태소 다중 발음사전을 사용하였다. 세가지 평가척도 중 빈도를 이용한 것의 성능이 가장 좋았고 여기에 제약조건을 반영하여 성능을 더 개선할 수 있었다. 특히 최대 결합 길이를 3으로 할 때의 성능이 가장 우수하여 언어모델 혼잡도는 117.9에서 97.3으로 18%감소했으며, 형태소 에러율 (MER: Morpheme error rate)은 21.3%에서 17.6%로 감소하였다. 이때 단음절 형태소는 54%에서 30%로 24%가 감소하였다.

시각장애인에게 상품을 안내하기 위한 객체 식별 알고리즘 (Object Detection Algorithm for Explaining Products to the Visually Impaired)

  • 박동연;임순범
    • 한국콘텐츠학회논문지
    • /
    • 제22권10호
    • /
    • pp.1-10
    • /
    • 2022
  • 시각장애인들은 상품들에 대한 점자 정보와 지원 시스템의 부재로 인해 소매점을 이용하는데 어려움을 겪고 있다. 그에 따라 본 연구에서는 소매점 내 상품을 인식하고, 이를 음성으로 해설하는 시스템의 기본 알고리즘을 제안한다. 우선, 딥러닝 모델이 입력 이미지에서 손 객체와 상품 객체를 감지한다. 그리고 각 객체의 좌표 정보를 계산하여 손 객체와 가장 많이 겹치는 상품 객체를 찾는다. 그 상품을 사용자가 선택한 상품이라고 판단한 뒤, 해당 상품의 대한 영양 정보를 Text-To-Speech를 사용하여 읽어준다. 평가 결과, 학습 모델의 성능이 높은 것을 확인하였다. 본 알고리즘은 시각장애인의 소매점 이용을 지원하는 시스템 구축에 적극적으로 활용될 수 있을 것이다.

개화기 과부개가 담론분석 -신문과 신소설을 중심으로- (A study of discourses on remarriage of the widows during the enlightenment period -Based on newspapers and Shinsoseol-)

  • 전미경
    • 가정과삶의질연구
    • /
    • 제19권3호
    • /
    • pp.17-29
    • /
    • 2001
  • This paper serves to analyze discourses on remarriage of the widows at the beginning of the modernization era or during the enlightenment period of Korea (1860-1910). The discourses of newspapers and Shinsoseol which are the text of this study have been analyzed with the qualitative research technique. The major conclusions that are derived from the study are as follows: First, intellectuals during the enlightenment period claimed the unfairness of the prohibition from remarriage of the widows with especially focusing on financial difficulty and life-long loneliness of the young widows. Second, permission of remarriage of the widows was explained not with the point of vies of individual life of widow, but with the point of vies of strengthening the international competitiveness. Third, the discourse claimed that the widow should hold the power of decision of remarriage. Forth, the discourse emphasized the etiquette of the wedding ceremony in remarriage of widows. Fifth, the point that the faithfulness was not easy for a usual widow to obey made the faithfulness noble ethical principle of Korea society.

  • PDF

상호작용 읽기전략을 통해서 본 한국 대학생들의 독해과정에 관한 연구 (Investigating English reading processes of Korean college students through reciprocal reading strategy)

  • 나경희;이선
    • 영어어문교육
    • /
    • 제11권4호
    • /
    • pp.209-235
    • /
    • 2005
  • The purpose of the present study was to investigate the effectiveness of reciprocal teaching procedure for improving Korean college students' reading comprehension of English text. In particular, this study sought to explore the qualitative features, if any, in students' use of reading comprehension strategies presented in the process of Reciprocal Reading Procedure (RRP). In order to accomplish the goal of the study, transcripts of the students' dialogues, open-ended questionnaires, and researchers' observation notes were examined. The results of the study showed that the participants used different four kinds of reading strategies in the process of RRP (questioning, clarifying, predicting, summarizing). The findings also suggested that the readers with limited knowledge of vocabulary had difficulty in moving on to the next level. Additionally, future research direction and some pedagogical implications are presented for the practical EFL classroom.

  • PDF

항공안전 데이터 분석 기반 항공기 감항관리체계 개선 방안 연구 (Feasibility Study of Aviation Safety Data Analysis for Airworthiness Management System Improvement)

  • 정현진;김승각;김용;심영민
    • 한국항공운항학회지
    • /
    • 제25권2호
    • /
    • pp.25-38
    • /
    • 2017
  • Current limitation of Aviation airworthiness manage system and text based Aviation safety report data, lack of Data Manage system for aviation parts failure and lack of continuing airworthiness related to task linking system for Inspection/Report/Improvement(AD ; Airworthiness Directive) have been apprehended to suggest direction of realizing improved operating system by applying aviation airworthiness manage system by using standardization and safety performance index based managing and safety performance index based data analyzing.

온라인 구매 행태를 고려한 토픽 모델링 기반 도서 추천 (Topic Modeling-based Book Recommendations Considering Online Purchase Behavior)

  • 정영진;조윤호
    • 지식경영연구
    • /
    • 제18권4호
    • /
    • pp.97-118
    • /
    • 2017
  • Thanks to the development of social media, general users become information and knowledge providers. But customers also feel difficulty to decide their purchases due to numerous information. Although recommender systems are trying to solve these information/knowledge overload problem, it may be asked whether they can honestly reflect customers' preferences. Especially, customers in book market consider contents of a book, recency, and price when they make a purchase. Therefore, in this study, we propose a methodology which can reflect these characteristics based on topic modeling and provide proper recommendations to customers in book market. Through experiments, our methodology shows higher performance than traditional collaborative filtering systems. Therefore, we expect that our book recommender system contributes the development of recommender systems studies and positively affect the customer satisfaction and management.

Development of a 3-D Visualization Application for Management of Substation Equipment

  • Park, Chang-Hyun
    • 조명전기설비학회논문지
    • /
    • 제23권3호
    • /
    • pp.38-44
    • /
    • 2009
  • This paper presents a new windows application based on 3-D graphics and Text-To-Speech (TTS) for effective management of substation equipment. When problems in a power system occur, inexperienced power system operators may have difficulty in understanding the situation as well as finding suitable countermeasures quickly. This paper addresses an effective scheme to visualizing power system equipment under normal and abnormal conditions using 3-D graphics and animations. In addition, the state variations and the order of maintenance priority of substation equipment are represented by TTS and intuitive methods. The proposed system can help power system operators to more quickly understand the state of power system equipment, and it can provide operators with the suitable countermeasures for minimizing damage caused by equipment problems.

Development of voice pen-pal application of global communication system by voice message

  • Lau, Shuai
    • 한국인공지능학회지
    • /
    • 제2권1호
    • /
    • pp.1-3
    • /
    • 2014
  • These days, interest and demand on smart learning has rapidly increased. Video English and mobile system based English speaking service have become popular. This study gave prototype of application to give and take voice message with world people and to give new concept of voice pen-pal beyond exchange of text messages. In modern society having rapidly increasing demand on smart learning, you can study foreign language by smart phone and communicate with foreigners by voice anytime and anywhere. The app allows global exchange to learn conversation. Recruitment of initial users and profit model have problems. We shall develop to improve problems and to solve difficulty.