Centroid-based summarization of multiple documents: sentence extraction, utility-based evaluation, and user studies

2000/05/12 by Dragomir R. Radev, Hongyan Jing, Malgorzata Budzikowska
Computer Science · #cs.CL #cs.AI #cs.DL #cs.HC #cs.IR

paper · pdf

published as NAACL/ANLP Workshop on Automatic Summarization, Seattle, WA, April 30, 2000 · 10 pages Corpus availability at http://perun.si.umich.edu/~radev/mds

arxiv created 2000/05/12 · arxiv updated 2009/11/30

Abstract

We present a multi-document summarizer, called MEAD, which generates summaries using cluster centroids produced by a topic detection and tracking system. We also describe two new techniques, based on sentence utility and subsumption, which we have applied to the evaluation of both single and multiple document summaries. Finally, we describe two user studies that test our models of multi-document summarization.

Related

• Revisiting the Centroid-based Method: A Strong Baseline for Multi-Document Summarization
• Supervising the Centroid Baseline for Extractive Multi-Document Summarization
• Centrality Meets Centroid: A Graph-based Approach for Unsupervised Document Summarization
• Multi-Document Summarization with Centroid-Based Pretraining
• Multi-Document Summarization using Distributed Bag-of-Words Model