A Query Specific Graph Based Approach to Multi-document Text Summarization: Simultaneous Cluster and Sentence Ranking

Author

Pandit, Sandip R. ; Potey, M.A.

Author_Institution

Dept. of Comput. Eng., D.Y. Patil Coll. of Eng., Pune, India

fYear

2013

fDate

21-23 Dec. 2013

Firstpage

213

Lastpage

217

Abstract

Recently the focus of query independent summary is shifted to query specific document summarization. This paper presents a graph based method to find query specific multi-document summarization. Our system is divided into two stages, off-line and on-line. We construct document as graph by considering paragraph as nodes in off-line stage. Edge scores are represented node similarities. In online stage, query specific weight are calculated and assigned to node. We then perform keyword search on the document graph and search a minimum top spanning tree for finding relevant nodes that satisfy the keyword search. Resultant summary looks coherent due to simultaneous cluster and sentence ranking. Experimental results for multi-document scenarios are encouraging.

Keywords

graph theory; pattern clustering; query processing; text analysis; cluster ranking; edge score; keyword search; multidocument text summarization; node similarity; paragraph; query independent summary; query specific graph based approach; query specific weight; sentence ranking; Clustering algorithms; Computers; Educational institutions; Keyword search; Machine intelligence; Redundancy; Semantics; Minimum spanning tree; Pre-processing; Query-specific Summarization; Stop Word; ranking;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Intelligence and Research Advancement (ICMIRA), 2013 International Conference on

Conference_Location

Katra

Type

conf

DOI

10.1109/ICMIRA.2013.47

Filename

6918824