The anatomy of a large-scale hypertextual Web search engine
WWW7 Proceedings of the seventh international conference on World Wide Web 7
Query-sensitive similarity measures for the calculation of interdocument relationships
Proceedings of the tenth international conference on Information and knowledge management
Automatic evaluation of summaries using N-gram co-occurrence statistics
NAACL '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1
Query-sensitive similarity measures for information retrieval
Knowledge and Information Systems
Query-Sensitive Similarity Measure for Content-Based Image Retrieval
ICDM '06 Proceedings of the Sixth International Conference on Data Mining
Graph-based ranking algorithms for sentence extraction, applied to text summarization
ACLdemo '04 Proceedings of the ACL 2004 on Interactive poster and demonstration sessions
Extractive summarization using inter- and intra- event relevance
ACL-44 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics
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
Using Cross-Document Random Walks for Topic-Focused Multi-Document
WI '06 Proceedings of the 2006 IEEE/WIC/ACM International Conference on Web Intelligence
LexRank: graph-based lexical centrality as salience in text summarization
Journal of Artificial Intelligence Research
Hi-index | 0.00 |
In this paper, we investigate how to combine the link-aware and link-free information in sentence ranking for query-oriented summarization. Although the link structure has been emphasized in the existing graph-based summarization models, there is lack of pertinent analysis on how to use the links. By contrasting the text graph with the web graph, we propose to evaluate significance of sentences based on neighborhood graph model. Taking the advantage of the link information provided on the graph, each sentence is evaluated according to its own value as well as the cumulative impacts from its neighbors. For a task like query-oriented summarization, it is critical to explore how to reflect the influence of the query. To better incorporate query information into the model, we further design a query-sensitive similarity measure to estimate the association between a pair of sentences. When evaluated on DUC 2005 dataset, the results of the pro-posed approach are promising.