Verb classification using distributional similarity in syntactic and semantic structures

  • Authors:
  • Danilo Croce;Roberto Basili;Alessandro Moschitti;Martha Palmer

  • Affiliations:
  • University of Tor Vergata, Roma, Italy;University of Tor Vergata, Roma, Italy;University of Trento, Povo (TN), Italy;University of Colorado at Boulder, Boulder, CO

  • Venue:
  • ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 1
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we propose innovative representations for automatic classification of verbs according to mainstream linguistic theories, namely VerbNet and FrameNet. First, syntactic and semantic structures capturing essential lexical and syntactic properties of verbs are defined. Then, we design advanced similarity functions between such structures, i.e., semantic tree kernel functions, for exploiting distributional and grammatical information in Support Vector Machines. The extensive empirical analysis on VerbNet class and frame detection shows that our models capture meaningful syntactic/semantic structures, which allows for improving the state-of-the-art.