Evaluating sentence compression: pitfalls and suggested remedies

  • Authors:
  • Courtney Napoles;Benjamin Van Durme;Chris Callison-Burch

  • Affiliations:
  • Johns Hopkins University;Johns Hopkins University;Johns Hopkins University

  • Venue:
  • MTTG '11 Proceedings of the Workshop on Monolingual Text-To-Text Generation
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

This work surveys existing evaluation methodologies for the task of sentence compression, identifies their shortcomings, and proposes alternatives. In particular, we examine the problems of evaluating paraphrastic compression and comparing the output of different models. We demonstrate that compression rate is a strong predictor of compression quality and that perceived improvement over other models is often a side effect of producing longer output.