Paper Info
Title
Improving Diversity of Focused Summaries through the Negative Endorsements of Redundant Facts
Abstract
We present NegativeRank, a novel graph-based sentence ranking model to improve the diversity of focused summary by performing random walks over sentence graph with negative edge weights. Unlike the typical eigenvector centrality ranking, our method models the redundancy among sentence nodes as the negative edges. The negative edges can be thought of as the propagation of disapproval votes which can be used to penalize redundant sentences. As the iterative process continues, the initial ranking score of a given node will be adjusted according to a long-term negative endorsement from other sentence nodes. The evaluation results confirm that our proposed method is very effective in improving the diversity of the focused summary, compared to several well-known text summarization methods.
Year
DOI
Venue
2010
10.1109/WI-IAT.2010.36
Web Intelligence
Keywords
Field
DocType
graph theory,text analysis,NegativeRank,focused summaries diversity,graph-based sentence ranking model,negative edge weights,random walks,redundant facts negative endorsements,sentence graph,text summarization methods,diversity,focused summarization,negative edges,random walks,sentence graph
Graph theory,Data mining,Automatic summarization,Graph,Ranking,Information retrieval,Iterative and incremental development,Computer science,Random walk,Redundancy (engineering),Sentence
Conference
Volume
Citations 
PageRank 
1
0
0.34
References 
Authors
15
6
Name
Order
Citations
PageRank
Palakorn Achananuparp130223.16
Xiaohua Hu22819314.15
Lifan Guo3364.94
Tingting He434861.04
Yuan An511714.51
Zhoujun Li6964115.99