Statistical Relational Learning to Recognise Textual Entailment

  • Miguel Rios
  • Lucia Specia
  • Alexander Gelbukh
  • Ruslan Mitkov
Conference paper

DOI: 10.1007/978-3-642-54906-9_27

Part of the Lecture Notes in Computer Science book series (LNCS, volume 8403)
Cite this paper as:
Rios M., Specia L., Gelbukh A., Mitkov R. (2014) Statistical Relational Learning to Recognise Textual Entailment. In: Gelbukh A. (eds) Computational Linguistics and Intelligent Text Processing. CICLing 2014. Lecture Notes in Computer Science, vol 8403. Springer, Berlin, Heidelberg

Abstract

We propose a novel approach to recognise textual entailment (RTE) following a two-stage architecture – alignment and decision – where both stages are based on semantic representations. In the alignment stage the entailment candidate pairs are represented and aligned using predicate-argument structures. In the decision stage, a Markov Logic Network (MLN) is learnt using rich relational information from the alignment stage to predict an entailment decision. We evaluate this approach using the RTE Challenge datasets. It achieves the best results for the RTE-3 dataset and shows comparable performance against the state of the art approaches for other datasets.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • Miguel Rios
    • 1
  • Lucia Specia
    • 2
  • Alexander Gelbukh
    • 3
  • Ruslan Mitkov
    • 1
  1. 1.Research Group in Computational LinguisticsUniversity of WolverhamptonWolverhamptonUK
  2. 2.Department of Computer ScienceUniversity of SheffieldSheffieldUK
  3. 3.Centro de Investigación en ComputaciónInstituto Politécnico NacionalMexico CityMexico

Personalised recommendations