Back to Main Conference 2004
LREC 2004main

Re-using High-quality Resources for Continued Evaluation of Automated Summarization Systems

Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC 2004)

DOI:10.63317/4yz5d9naynh3

Abstract

In this paper we present a method for re-using the human judgements on summary quality provided by the DUC contest. The score to be awarded to automatic summaries is calculated as a function of the scores assigned manually to the most similar summaries for the same document. This approach enhances the standard n-gram based evaluation of automatic summarization systems by establishing similarities between {\it extractive} (vs. {\it abstractive}) summaries and by taking advantage of the big quantity of evaluated summaries available from the DUC contest. The utility of this method is exemplified by the improvements achieved on a headline production system.

Details

Paper ID
lrec2004-main-278
Pages
N/A
BibKey
alonso-etal-2004-using
Editor
N/A
Publisher
European Language Resources Association (ELRA)
ISSN
2522-2686
ISBN
2-9517408-1-6
Conference
Fourth International Conference on Language Resources and Evaluation
Location
Lisbon, Portugal
Date
26 May 2004 28 May 2004

Authors

  • LA

    Laura Alonso

  • MF

    Maria Fuentes

  • MM

    Marc Massot

  • HR

    Horacio Rodríguez

Links