Extractive multi-document summaries should explicitly not contain document-specific content

Authors:
Rebecca Mason;Eugene Charniak
Affiliations:
Brown University, Providence, RI;Brown University, Providence, RI
Venue:
WASDGML '11 Proceedings of the Workshop on Automatic Summarization for Different Genres, Media, and Languages
Year:
2011

Citing 6
Cited 1

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
Bayesian query-focused summarization

ACL-44 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics
Exploring content models for multi-document summarization

NAACL '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Contrastive summarization: an experiment with consumer reviews

NAACL-Short '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers
A hybrid hierarchical model for multi-document summarization

ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Non-expert evaluation of summarization systems is risky

CSLDAMT '10 Proceedings of the NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk

DualSum: a topic-model based approach for update summarization

EACL '12 Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Unsupervised approaches to multi-document summarization consist of two steps: finding a content model of the documents to be summarized, and then generating a summary that best represents the most salient information of the documents. In this paper, we present a sentence selection objective for extractive summarization in which sentences are penalized for containing content that is specific to the documents they were extracted from. We modify an existing system, Hier-Sum (Haghighi & Vanderwende, 2009), to use our objective, which significantly outperforms the original HierSum in pairwise user evaluation. Additionally, our ROUGE scores advance the current state-of-the-art for both supervised and unsupervised systems with statistical significance.