Revisiting optimal decoding for machine translation IBM model 4

Authors:
Sebastian Riedel;James Clarke
Affiliations:
University of Tokyo, Japan and Research Organization of Information and System, Japan;University of Illinois at Urbana-Champaign, Urbana, IL
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 4
Cited 1

The mathematics of statistical machine translation: parameter estimation

Computational Linguistics - Special issue on using large corpora: II
Fast and optimal decoding for machine translation

Artificial Intelligence
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
Incremental integer linear programming for non-projective dependency parsing

EMNLP '06 Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing

Exact decoding of phrase-based translation models through Lagrangian relaxation

EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper revisits optimal decoding for statistical machine translation using IBM Model 4. We show that exact/optimal inference using Integer Linear Programming is more practical than previously suggested when used in conjunction with the Cutting-Plane Algorithm. In our experiments we see that exact inference can provide a gain of up to one BLEU point for sentences of length up to 30 tokens.