Multi-document summarization refers to the process of automatic extraction of text from multiple sources which belong to same topic. With the increase in usage of internet large amount of data has been generated day by day. It is quite difficult for anyone to distinguish and summarize this vast information gathered from various sources. Multi document text summarization has solution for this problem. Multi document summarization assembles information from different sources and summarizes the information up to necessary length. In this paper preprocessing is applied to unprocessed documents and different features are extracted. And then CST relations are identified from these extracted features document. Finally summary is generated depending on identified CST relations.

Multi Document Summarization, CST Realtions, Feature Extraction, Extractive Summarization.

[1] V. Gupta and G. S. Lehal, "A survey of text summarization extractive techniques," Journal of Emerging Technologies in Web Intelligence, vol. 2, pp. 258-268, 2010.
[2] Yogan Jaya Kumar, Naomie Salim, Albaraa Abuobieda, Ameer Tawfik, “Multi Document summarization based on cross-document relation using voting technique”, International conference on computing, electrical and electronic engineering (ICCEEE), 2013.
[3] Y. J. Kumar and N. Salim, "Automatic multi document summarization approaches," Journal of Computer Science, vol. 8, pp. 133-140, 2011.
[4] Ultimate Research Assistant, http://en.wikipedia.org/wiki/Ultimate_Research_Assistant, 27 Jan,2015.
[5] D. R. Radev, "A common theory of information fusion from multiple text sources step one: cross-document structure," presented at the Proceedings of the 1st SIGdial workshop on Discourse and dialogue – Volume 10, HongKong, 2000
[6] D. R. Hsun-Hui Huang, Horng-Chang Yang, Yau-Hwang kuo, “A Fuzzy-Rough Hybrid Approach to Multi-document Extractive Summarization” , Ninth International Conference on Hybrid Intelligent Systems, 2009
[7] Md. Mohsin Ali , Monotosh Kumar Ghosh, and Abdullah-Al-Mamun, “Multi-document Text Summarization: SimWithFirst Based Features and Sentence Co-selection Based Evaluation”, International Conference on Future Computer and Communication, 2009
[8] Z. Zhang, S. Blair-Goldensohn, and D. R. Radev, "Towards CST-enhanced summarization," presented atthe Eighteenth national conference on Artificial intelligence, Edmonton, Alberta, Canada, 2002
[9] M. L. d. R. C. Jorge and T. A. S. Pardo, "Experiments with CST-based multidocument summarization," presented at the Proceedings of the 2010 Workshop on Graph-based Methods for Natural Language Processing, Uppsala, Sweden, 2010
[10] Z. Zhang, J. Otterbacher, and D. Radev, "Learning crossdocument structural relationships using boosting," presented at the Proceedings of the twelfth international conference on Information and knowledge management, New Orleans, LA, USA, 2003.
[11] Rajesh S.Prasad, Dr. U.V.Kulkarni, Jayashree R.Prasad, “A Novel Evolutionary Connectionist Text Summarizer (ECTS)”, published in proceedingASID’09 Proceedings of the 3rd international conference on Anti-Counterfeiting, security, and identification in communication, IEEE Press Piscataway, NJ, USA, 20 Aug 2009