Stochastic lexicalized inversion transduction grammar for alignment

  • Authors:
  • Hao Zhang;Daniel Gildea

  • Affiliations:
  • University of Rochester, Rochester, NY;University of Rochester, Rochester, NY

  • Venue:
  • ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present a version of Inversion Transduction Grammar where rule probabilities are lexicalized throughout the synchronous parse tree, along with pruning techniques for efficient training. Alignment results improve over unlexicalized ITG on short sentences for which full EM is feasible, but pruning seems to have a negative impact on longer sentences.