Carnegie Mellon University
Browse
file.pdf (821.16 kB)

Multi-Document Summarization By Sentence Extraction

Download (821.16 kB)
journal contribution
posted on 2000-01-01, 00:00 authored by Jade Goldstein, Vibhu Mittal, Jaime G. Carbonell, Mark Kantrowitz

This paper discusses a text extraction approach to multi-document summarization that builds on single-document summarization methods by using additional, available information about the document set as a whole and the relationships between the documents. Multi-document summarization differs from single in that the issues of compression, speed, redundancy and passage selection are critical in the formation of useful summaries. Our approach addresses these issues by using domain-independent techniques based mainly on fast, statistical processing, a metric for reducing redundancy and maximizing diversity in the selected passages, and a modular framework to allow easy parameterization for different genres, corpora characteristics and user requirements.

History

Date

2000-01-01

Usage metrics

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC