A machine learning approach to textual entailment recognition

  • Authors:
  • Fabio massimo Zanzotto;Marco Pennacchiotti;Alessandro Moschitti

  • Affiliations:
  • Disp, university of rome ‘tor vergata’, roma, italy e-mail: zanzotto@info.uniroma2.it;Computerlinguistik, universität des saarlandes, saarbrücken, germany e-mail: pennacchiotti@coli.uni-sb.de;Disi, university of trento, povo di trento, italy e-mail: moschitti@disi.unitn.it

  • Venue:
  • Natural Language Engineering
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Designing models for learning textual entailment recognizers from annotated examples is not an easy task, as it requires modeling the semantic relations and interactions involved between two pairs of text fragments. In this paper, we approach the problem by first introducing the class of pair feature spaces, which allow supervised machine learning algorithms to derive first-order rewrite rules from annotated examples. In particular, we propose syntactic and shallow semantic feature spaces, and compare them to standard ones. Extensive experiments demonstrate that our proposed spaces learn first-order derivations, while standard ones are not expressive enough to do so.