Better word alignments with supervised ITG models

  • Authors:
  • Aria Haghighi;John Blitzer;John DeNero;Dan Klein

  • Affiliations:
  • University of California at Berkeley;University of California at Berkeley;University of California at Berkeley;University of California at Berkeley

  • Venue:
  • ACL '09 Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 2 - Volume 2
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

This work investigates supervised word alignment methods that exploit inversion transduction grammar (ITG) constraints. We consider maximum margin and conditional likelihood objectives, including the presentation of a new normal form grammar for canonicalizing derivations. Even for non-ITG sentence pairs, we show that it is possible learn ITG alignment models by simple relaxations of structured discriminative learning objectives. For efficiency, we describe a set of pruning techniques that together allow us to align sentences two orders of magnitude faster than naive bitext CKY parsing. Finally, we introduce many-to-one block alignment features, which significantly improve our ITG models. Altogether, our method results in the best reported AER numbers for Chinese-English and a performance improvement of 1.1 BLEU over GIZA++ alignments.