Centroid-based summarization of multiple documents
Information Processing and Management: an International Journal
Robust generic and query-based summarisation
EACL '03 Proceedings of the tenth conference on European chapter of the Association for Computational Linguistics - Volume 2
Sentence Fusion for Multidocument News Summarization
Computational Linguistics
Graph-based ranking algorithms for sentence extraction, applied to text summarization
ACLdemo '04 Proceedings of the ACL 2004 on Interactive poster and demonstration sessions
Using random walks for question-focused sentence retrieval
HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
LexRank: graph-based lexical centrality as salience in text summarization
Journal of Artificial Intelligence Research
Manifold-ranking based topic-focused multi-document summarization
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Query-focused multi-document summarization based on query-sensitive feature space
Proceedings of the 21st ACM international conference on Information and knowledge management
Combining co-clustering with noise detection for theme-based summarization
ACM Transactions on Speech and Language Processing (TSLP)
Information Sciences: an International Journal
Hi-index | 0.00 |
Query-focused multi-document summarization aims to create a compressed summary biased to a given query. This paper presents a context-sensitive approach based on manifold ranking of sentences to this summarization task. The proposed context enhanced manifold ranking approach not only looks at the sentence itself, but also considers its surrounding contextual information. Compared to the existing manifold ranking approach which totally ignores the contextual information of a sentence, this approach can capture more additional relevant information which is especially necessary for formulating the relationships between short text snippets like sentences. Experiments are conducted on the DUC 2005 and DUC 2006 data sets and the ROUGE evaluation results demonstrate the advantages of the proposed approach.