¡¡Chinese Journal of Computers   Full Text
  TitleMulti-Document Automatic Summarization Technique Based on Information Fusion
  AuthorsXU Yong-Dong XU Zhi-Ming WANG Xiao-Long
  Address(Intelligent Technology & Natural Language Processing Laboratory, School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001)
  Year2007
  IssueNo.11(2048¡ª2054)
  Abstract &
  Background 		Abstract A Multiple Documents Framework(MDF) is proposed for multi-document automatic summarization task. By representing interrelationship between text units at different levels of granularity and the happen and change of various events at time dimension, this framework can achieve information fusion of multi-document while reserve original information of set of related documents. MDF simplifies traditional multi-document representation in cross structure theory and simultaneously, supplements change and distribution informations of events topics which cannot be obtained in information fusion theory. Concretely, a series of algorithms including building MDF, multi-document information fusion based MDF and summarization generation are proposed. The capability of concurrently fusing multiple knowledge sources of MDF strategies is testified by experiments in 32 different sets of net documents and shows good results.

keywords multiple document framework; multi-document automatic summarization; information fusion; time

background This work is sponsored by key project of National Nature Science Foundation of China (60435020). The project name is "Research of Question-Answering Information Retrieval Technique". In order to improve quality of retrieval system, this project uses multi-document automatic summarization to extract important content from retrieval results and return final answer to users. As the post-processing part of project, the work in this paper exceedingly affects the result of retrieval system. Before this project, the research term has accomplished relative project of National Natural Science Foundation of China(60373100) named by "Multi-document Automatic Summarization Based on Logistic Frames" which studies Chinese multiple documents automatic summarization for extensive Web information process task.