Incorporating cross-document relationships between sentences for single document summarizations

Authors:
Xiaojun Wan;Jianwu Yang;Jianguo Xiao
Affiliations:
Institute of Computer Science and Technology, Peking University, Beijing, China;Institute of Computer Science and Technology, Peking University, Beijing, China;Institute of Computer Science and Technology, Peking University, Beijing, China
Venue:
ECDL'06 Proceedings of the 10th European conference on Research and Advanced Technology for Digital Libraries
Year:
2006

Citing 21
Cited 0

Pictures of relevance: a geometric analysis of similarity measures

Journal of the American Society for Information Science
A trainable document summarizer

SIGIR '95 Proceedings of the 18th annual international ACM SIGIR conference on Research and development in information retrieval
The use of MMR, diversity-based reranking for reordering documents and producing summaries

Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval
The anatomy of a large-scale hypertextual Web search engine

WWW7 Proceedings of the seventh international conference on World Wide Web 7
New Methods in Automatic Extracting

Journal of the ACM (JACM)
Authoritative sources in a hyperlinked environment

Journal of the ACM (JACM)
Efficient text summarization using lexical chains

Proceedings of the 5th international conference on Intelligent user interfaces
Generic text summarization using relevance measure and latent semantic analysis

Proceedings of the 24th annual international ACM SIGIR conference on Research and development in information retrieval
A new approach to unsupervised text summarization

Proceedings of the 24th annual international ACM SIGIR conference on Research and development in information retrieval
Text summarization via hidden Markov models

Proceedings of the 24th annual international ACM SIGIR conference on Research and development in information retrieval
Using sentence-selection heuristics to rank text segments in TXTRACTOR

Proceedings of the 2nd ACM/IEEE-CS joint conference on Digital libraries
The use of unlabeled data to improve supervised learning for text summarization

SIGIR '02 Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval
Generic summarization and keyphrase extraction using mutual reinforcement principle and sentence clustering

SIGIR '02 Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval
Summarization beyond sentence extraction: a probabilistic approach to sentence compression

Artificial Intelligence
Sentence reduction for automatic text summarization

ANLC '00 Proceedings of the sixth conference on Applied natural language processing
Cut and paste based text summarization

NAACL 2000 Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference
The automated acquisition of topic signatures for text summarization

COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 1
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
Improving web search results using affinity graph

Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval
Automated text summarization and the SUMMARIST system

TIPSTER '98 Proceedings of a workshop on held at Baltimore, Maryland: October 13-15, 1998
The automatic creation of literature abstracts

IBM Journal of Research and Development

Quantified Score

Hi-index	0.00

Visualization

Abstract

Graph-based ranking algorithms have recently been proposed for single document summarizations and such algorithms evaluate the importance of a sentence by making use of the relationships between sentences in the document in a recursive way. In this paper, we investigate using other related or relevant documents to improve summarization of one single document based on the graph-based ranking algorithm. In addition to the within-document relationships between sentences in the specified document, the cross-document relationships between sentences in different documents are also taken into account in the proposed approach. We evaluate the performance of the proposed approach on DUC 2002 data with the ROUGE metric and results demonstrate that the cross-document relationships between sentences in different but related documents can significantly improve the performance of single document summarization.