@inproceedings{e7f2f591389d4fc09f80645ab7321750,
title = "Simultaneous Clustering and Noise Detection for Theme-based Summarization",
abstract = "Multi-document summarization aims to produce a concise summary that contains salient information from a set of source documents. Since documents often cover a number of topical themes with each theme represented by a cluster of highly related sentences, sentence clustering plays a pivotal role in theme-based summarization. Moreover, noting that real-world datasets always contain noises which inevitably degrade the clustering performance, we incorporate noise detection with spectral clustering to generate ordinary sentence clusters and one noise sentence cluster. We are also interested in making the theme-based summaries biased towards a user's query. The effectiveness of the proposed approaches is demonstrated by both the cluster quality analysis and the summarization evaluation conducted on the DUC generic and query-oriented summarization datasets.",
author = "Xiaoyan Cai and Renxian Zhang and Dehong Gao and Wenjie Li",
note = "Publisher Copyright: {\textcopyright} 2011 AFNLP; 5th International Joint Conference on Natural Language Processing, IJCNLP 2011 ; Conference date: 08-11-2011 Through 13-11-2011",
year = "2011",
language = "English",
series = "IJCNLP 2011 - Proceedings of the 5th International Joint Conference on Natural Language Processing",
publisher = "Association for Computational Linguistics (ACL)",
pages = "491--499",
editor = "Haifeng Wang and David Yarowsky",
booktitle = "IJCNLP 2011 - Proceedings of the 5th International Joint Conference on Natural Language Processing",
address = "United States",
}