Earticle

초록

영어

In this paper, the method ofextract event from newspaper is proposed. First, the candidate sentences are select by using trigger word. Then, statistic models in three levels are consisted of extract model, which is sentences level, news level and topic level is used to extract event from candidate sentences and the probability of extracted events is calculated by three levels model. Finally, the method proposed in this paper is used to extract 4 type events. The experiment result shows this method have ideal effect on event extraction.

목차

Abstract
 1. Introduction
 2. Our Approach
 3. Concrete Design Procedures
  3.1. The Acquisition of Trigger Words
  3.2. The Model in Sentence Level
  3.3. The Model in News Level
  3.4. The Model in Topic Level
 4. Experimental Results
 5. Conclusions
 References

키워드

저자

• Jing Lu [ Institute of Computer Science and Technology, Peking University, Beijing, China, State Key Laboratory of Digital Publishing Technology (Peking University Founder Group Co. LTD.), Beijing, China, Postdoctoral Workstation of the Zhongguancun Haidian Science Park, Beijing, China ]
• Mao Ye [ State Key Laboratory of Digital Publishing Technology (Peking University Founder Group Co. LTD.), Beijing, China ]
• Zhi Tang [ Institute of Computer Science and Technology, Peking University, Beijing, China, State Key Laboratory of Digital Publishing Technology (Peking University Founder Group Co. LTD.), Beijing, China ]
• Xiao-Jun Huang [ State Key Laboratory of Digital Publishing Technology (Peking University Founder Group Co. LTD.), Beijing, China ]
• Jia-Le Ma [ State Key Laboratory of Digital Publishing Technology (Peking University Founder Group Co. LTD.), Beijing, China ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Signal Processing, Image Processing and Pattern Recognition

• 간기

  격월간

• pISSN

  2005-4254

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605