The Study on Multiple Document Automatic Summarization System

(*) Corresponding author

Authors' affiliations

DOI's assignment:
the author of the article can submit here a request for assignment of a DOI number to this resource!
Cost of the service: euros 10,00 (for a DOI)


Multi-document summarization is a technology of natural languages processing, which extract important information from multiple texts about the same topic according to ratio of compression. Multi-document summarization becomes new research spot withincreasing of information in internet. The system mainly includes crawler module which crawls news from SINA finance website, data cleaning module which excludes repetitive information and summarization module which implements the function of sentence extracting. The program is based on the database platform system MySQL and MyEclipse development platform, which has strong visual feature and has good user interface, and convenience for users learn and use. The program also uses JAVA language in JSP and Struts2 development technologies, in this way, the program can easily implement its functions in website pages. The system has perfect function which can be operated easily. The interface is simple and effective reducing the difficulty and complexity of the operation.
Copyright © 2013 Praise Worthy Prize - All rights reserved.


Multi-Document Summarization; Nature Languages Processing; Sentence Extracting

Full Text:



Qin Bing, Liu Ting, Li Sheng, multi-document summarization Summary of Harbin Institute of Technology School of Computer Science Information Retrieval Laboratory, 150001

Qin Bing, Liu Ting, Chen Shanglin, Li Sheng, multi-document summarization sentence Optimized selection methods. Harbin Institute of Technology College of Computer Science and Technology Information Retrieval Laboratory, 150001

Wang Shan Sa Shi Xuan, Introduction to Database Systems., Beijing: Higher Education Press in 2006.

XU Yong-Dong, Wang Yadong, Liu Yang, the Wang Wei multi-document summarization sentences based on time information sort Strategies for the Harbin Institute of Technology (Weihai), College of Computer Science and Technology, 264209

Zhou Lizhu, Lin Ling. Focused crawling Research. Department of Computer Science and Technology, Beijing 100084, China

Qin Feng, Zhao Yanjun, Ze-Kai Cheng, Chen Qiming, Term rights based on entries mathematical expectation weight. Anhui University, School of Computer Science, Anhui Maanshan 243002

Liu Jinling. Semantic-based high-quality Chinese SMS text clustering algorithm. Huaiyin Institute of Technology Department of Computer Engineering, Huai'an 223003

XU Yong-Dong, Wang Yadong, Liu Yang, Wang Wei, the right light day multi-document summarization based on the time information of the sentence ordering strategy. Harbin Institute of Technology School of Computer Science, 264209

Teacher pulpit: Java Web Development the combat classic Basics (JSP, Servlet, Struts, Ajax). Tsinghua University Press, 2010.

Liu Xiaohua, Zhang Jian, JSP application development Detailed. Publishing House of Electronics Industry, 2007.1.


  • There are currently no refbacks.

Please send any question about this web site to
Copyright © 2005-2024 Praise Worthy Prize