- 권한신청
- P-ISSN1013-0799
- E-ISSN2586-2073
- KCI
사건중심 뉴스기사 자동요약을 위한 사건탐지 기법에 관한 연구
A Study on an Effective Event Detection Method for Event-Focused News Summarization
김용광 (연세대학교)
- 다운로드 수
- 조회수
초록
이 연구에서는 사건중심 뉴스기사 요약문을 자동생성하기 위해 뉴스기사들을 SVM 분류기를 이용하여 사건 주제범주로 먼저 분류한 후, 각 주제범주 내에서 싱글패스 클러스터링 알고리즘을 통해 특정한 사건 관련 기사들을 탐지하는 기법을 제안하였다. 사건탐지 성능을 높이기 위해 고유명사에 가중치를 부여하고, 뉴스의 발생시간을 고려한 시간벌점함수를 제안하였다. 또한 일정 규모 이상의 클러스터를 분할하여 적절한 크기의 사건 클러스터를 생성하도록 수정된 싱글패스 알고리즘을 사용하였다. 이 연구에서 제안한 사건탐지 기법의 성능은 단순 싱글패스 클러스터링 기법에 비해 정확률, 재현율, F-척도에서 각각 37.1%, 0.1%, 35.4%의 성능 향상률을 보였고, 오보율과 탐지비용에서는 각각 74.7%, 11.3%의 향상률을 나타냈다.
- keywords
- event detection, event-focused news summarization, support vector machine classifier, single pass algorithm, time penalty function, 사건탐지, 사건중심 뉴스기사 자동요약, 지지벡터기, 싱글패스 알고리즘, 시간벌점함수, event detection, event-focused news summarization, support vector machine classifier, single pass algorithm, time penalty function
Abstract
This study investigates an event detection method with the aim of generating an event-focused news summary from a set of news articles on a certain event using a multi-document summarization technique. The event detection method first classifies news articles into the event related topic categories by employing a SVM classifier and then creates event clusters containing news articles on an event by a modified single pass clustering algorithm. The clustering algorithm applies a time penalty function as well as cluster partitioning to enhance the clustering performance. It was found that the event detection method proposed in this study showed a satisfactory performance in terms of both the F-measure and the detection cost.
- keywords
- event detection, event-focused news summarization, support vector machine classifier, single pass algorithm, time penalty function, 사건탐지, 사건중심 뉴스기사 자동요약, 지지벡터기, 싱글패스 알고리즘, 시간벌점함수, event detection, event-focused news summarization, support vector machine classifier, single pass algorithm, time penalty function
참고문헌
정영미. (2005). 정보검색연구:구미무역(주)출판부..
한국언론연구원. (1991). 전국언론사 기사자료 표준분류표:한국언론연구원.
Allan, J. (2002). Topic Detection and Tracking Event based Information Organization:Kluwer Academic Publishers.
Chang, C. (2001). LIBSVM: a li- brary for support vector machines. http://www.csie.ntu.edu.tw/~cjlin/libsvm.
Dharanipragada, D. M. (2002). Segmentation and detection at ibm: hybrid statistical models and two-tiered clustering, in: Topic Detec- tion and Tracking Event based Infor- mation Organization:Kluwer Academic Publishers.
Leek, T. (2002). Probabilistic approaches to topic de- tection and Tracking, in: Topic Detection and Tracking Event based Information Organization:Kluwer Academic Publishers.
McKeown, K. R. (2002). Tracking and Sum- marizing News on a Daily Basis with Columbia’s Newsblaster (-). Proceedings of Human Language Technology Con- ference 2002(HLT 2002).
Papka, R. (1998). On-line new event detection using single pass clus- tering. .
Radev, D. R. (2000). Centroid-based summarization of multiple documents: sentence extraction, utility-based evaluation, and user stu- dies (21-30). NAACL/ANLP Workshop on Au- tomatic Summarization.
Radev, D. R. (2004). Centroid-based summarization of multiple documents. Information Pro- cessing & Management, 40(3), 919-938.
Walker, S. (1998). Okapi at TREC-6 automatic ad hoc, VLC, routing, filtering and QSDR (-). Proceedings of the Sixth Text Re- trieval Conference(TREC-6).
Yang, Y. (2000). Improving text cate- gorization methods for event tracking (-). Proceedings of the 23rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval: 65-72. ACM Press.
Yang, Y. (1999). Learning Approaches for De- tecting and Tracking News Events. IEEE Intelligent Systems, , 32-43.
- 다운로드 수
- 조회수
- 0KCI 피인용수
- 0WOS 피인용수