Dependency tree based sentence compression

  • Authors:
  • Katja Filippova;Michael Strube

  • Affiliations:
  • EML Research gGmbH, Heidelberg, Germany;EML Research gGmbH, Heidelberg, Germany

  • Venue:
  • INLG '08 Proceedings of the Fifth International Natural Language Generation Conference
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present a novel unsupervised method for sentence compression which relies on a dependency tree representation and shortens sentences by removing subtrees. An automatic evaluation shows that our method obtains result comparable or superior to the state of the art. We demonstrate that the choice of the parser affects the performance of the system. We also apply the method to German and report the results of an evaluation with humans.