Enhancing N-Gram-Based Summary Evaluation Using Information Content and a Taxonomy

  • Mijail Kabadjov
  • Josef Steinberger
  • Ralf Steinberger
  • Massimo Poesio
  • Bruno Pouliquen
Conference paper

DOI: 10.1007/978-3-642-12275-0_71

Part of the Lecture Notes in Computer Science book series (LNCS, volume 5993)
Cite this paper as:
Kabadjov M., Steinberger J., Steinberger R., Poesio M., Pouliquen B. (2010) Enhancing N-Gram-Based Summary Evaluation Using Information Content and a Taxonomy. In: Gurrin C. et al. (eds) Advances in Information Retrieval. ECIR 2010. Lecture Notes in Computer Science, vol 5993. Springer, Berlin, Heidelberg

Abstract

In this paper we propose a novel information-theoretic metric for automatic summary evaluation when model summaries are available as in the setting of the AESOP task of the Update Summarization track of the Text Analysis Conference (TAC). The metric is based on the concept of information content operationalized by using a taxonomy. Hereby, we present and discuss the results obtained at TAC 2009.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Mijail Kabadjov
    • 1
  • Josef Steinberger
    • 1
  • Ralf Steinberger
    • 1
  • Massimo Poesio
    • 2
    • 3
  • Bruno Pouliquen
    • 1
  1. 1.Joint Research CentreEuropean CommissionIspraItaly
  2. 2.University of EssexColchesterUnited Kingdom
  3. 3.Universitá di TrentoPovoItaly

Personalised recommendations