Graph Based Query Specific Multi-document Text Summarization

Recently the focus of query independent summary is shifted to query specific document. This book presents a graph based method to find query specific multi-document summarization. Our system is divided into two stages, of- fline and online. We construct document as graph by con- sidering paragraph as nodes in offline 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.

Autorentext

Prof. Sandip Ramkrishna Pandit is currently working as an Assistant Professor in Amurtvahini College of Engineering, Sangamner, India. He has 10 international publications in various national, international journals and conferences. Being a silent researcher he is always trying new things in his curriculum.