Example-based rescoring of statistical machine translation output

Authors:
Michael Paul;Eiichiro Sumita;Seiichi Yamamoto
Affiliations:
ATR Spoken Language Translation Labs, Keihanna Science City, Kyoto, Japan and Kobe University, Kobe, Japan;ATR Spoken Language Translation Labs, Keihanna Science City, Kyoto, Japan;ATR Spoken Language Translation Labs, Keihanna Science City, Kyoto, Japan and Kobe University, Kobe, Japan
Venue:
HLT-NAACL-Short '04 Proceedings of HLT-NAACL 2004: Short Papers
Year:
2004

Citing 6
Cited 0

A framework of a mechanical translation between Japanese and English by analogy principle

Proc. of the international NATO symposium on Artificial and human intelligence
The String-to-String Correction Problem

Journal of the ACM (JACM)
The mathematics of statistical machine translation: parameter estimation

Computational Linguistics - Special issue on using large corpora: II
A new quantitative quality measure for machine translation systems

COLING '92 Proceedings of the 14th conference on Computational linguistics - Volume 2
Fast decoding and optimal decoding for machine translation

ACL '01 Proceedings of the 39th 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

Quantified Score

Hi-index	0.00

Visualization

Abstract

Conventional statistical machine translation (SMT) approaches might not be able to find a good translation due to problems in its statistical models (due to data sparseness during the estimation of the model parameters) as well as search errors during the decoding process. This paper1 presents an example-based rescoring method that validates SMT translation candidates and judges whether the selected decoder output is good or not. Given such a validation filter, defective translations can be rejected. The experiments show a drastic improvement in the overall system performance compared to translation selection methods based on statistical scores only.