Bidirectional phrase-based statistical machine translation

Authors:
Andrew Finch;Eiichiro Sumita
Affiliations:
NICT, Keihanna Science City, Kyoto, Japan;NICT, Keihanna Science City, Kyoto, Japan
Venue:
EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 3 - Volume 3
Year:
2009

Citing 7
Cited 1

The mathematics of statistical machine translation: parameter estimation

Computational Linguistics - Special issue on using large corpora: II
Bidirectional decoding for statistical machine translation

COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
Discriminative training and maximum entropy models for statistical machine translation

ACL '02 Proceedings of the 40th Annual Meeting on Association for 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
Automatic evaluation of machine translation quality using n-gram co-occurrence statistics

HLT '02 Proceedings of the second international conference on Human Language Technology Research
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

Enhancing language models in statistical machine translation with backward n-grams and mutual information triggers

HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper investigates the effect of direction in phrase-based statistial machine translation decoding. We compare a typical phrase-based machine translation decoder using a left-to-right decoding strategy to a right-to-left decoder. We also investigate the effectiveness of a bidirectional decoding strategy that integrates both mono-directional approaches, with the aim of reducing the effects due to language specificity. Our experimental evaluation was extensive, based on 272 different language pairs, and gave the surprising result that for most of the language pairs, it was better decode from right-to-left than from left-to-right. As expected the relative performance of left-to-right and right-to-left strategies proved to be highly language dependent. The bidirectional approach outperformed the both the left-to-right strategy and the right-to-left strategy, showing consistent improvements that appeared to be unrelated to the specific languages used for translation. Bidirectional decoding gave rise to an improvement in performance over a left-to-right decoding strategy in terms of the BLEU score in 99% of our experiments.