Learning non-isomorphic tree mappings for machine translation

  • Authors:
  • Jason Eisner

  • Affiliations:
  • Johns Hopkins Univ.

  • Venue:
  • ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 2
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

Often one may wish to learn a tree-to-tree mapping, training it on unaligned pairs of trees, or on a mixture of trees and strings. Unlike previous statistical formalisms (limited to isomorphic trees), synchronous TSG allows local distortion of the tree topology. We reformulate it to permit dependency trees, and sketch EM/Viterbi algorithms for alignment, training, and decoding.