Work

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

Year: 2000

Type: preprint

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.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.cs/0005020

Authors: Radev, Dragomir R., Jing, Hongyan, Budzikowska, Malgorzata

Institutions: University of Michigan, Columbia University, IBM Research - Thomas J. Watson Research Center

Language: English

Topic: Advanced Text Analysis Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W2953285682

Cites: 3

Cited by: 135

Related to: 10