Cohesive constraints in a beam search phrase-based decoder

Authors:
Nguyen Bach;Stephan Vogel;Colin Cherry
Affiliations:
Carnegie Mellon University, Pittsburgh, PA;Carnegie Mellon University, Pittsburgh, PA;Microsoft Research, One Microsoft Way, Redmond, WA
Venue:
NAACL-Short '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers
Year:
2009

Citing 6
Cited 4

A systematic comparison of various statistical alignment models

Computational Linguistics
BLEU: a method for automatic evaluation of machine translation

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Minimum error rate training in statistical machine translation

ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Phrasal cohesion and statistical machine translation

EMNLP '02 Proceedings of the ACL-02 conference on Empirical methods in natural language processing - Volume 10
Moses: open source toolkit for statistical machine translation

ACL '07 Proceedings of the 45th Annual Meeting of the ACL on Interactive Poster and Demonstration Sessions
Imposing constraints from the source tree on ITG constraints for SMT

SSST '08 Proceedings of the Second Workshop on Syntax and Structure in Statistical Translation

Improving Arabic-to-English statistical machine translation by reordering post-verbal subjects for alignment

ACLShort '10 Proceedings of the ACL 2010 Conference Short Papers
Soft dependency constraints for reordering in hierarchical phrase-based translation

EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Soft syntactic constraints for Arabic---English hierarchical phrase-based translation

Machine Translation
Improved Arabic-to-English statistical machine translation by reordering post-verbal subjects for word alignment

Machine Translation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Cohesive constraints allow the phrase-based decoder to employ arbitrary, non-syntactic phrases, and encourage it to translate those phrases in an order that respects the source dependency tree structure. We present extensions of the cohesive constraints, such as exhaustive interruption count and rich interruption check. We show that the cohesion-enhanced decoder significantly outperforms the standard phrase-based decoder on English→Spanish. Improvements between 0.5 and 1.2 BLEU point are obtained on English→Iraqi system.