Abstract

We describe a method for incorporating syntactic information in statistical machine translation systems. The first step of the method is to parse the source language string that is being translated. The second step is to apply a series of transformations to the parse tree, effectively reordering the surface string on the source language side of the translation system. The goal of this step is to recover an underlying word order that is closer to the target language word-order than the original string. The reordering approach is applied as a pre-processing step in both the training and decoding phases of a phrase-based statistical MT system. We describe experiments on translation from German to English, showing an improvement from 25.2 % Bleu score for a baseline system to 26.8 % Bleu score for the system with reordering, a statistically significant improvement.

Citations

1790	An Introduction to the Bootstrap - Efron, Tibshirani - 1993
846	A Maximum Entropy Approach to Natural Language Processing - Berger, Pietra, et al. - 1996
102	Statistical Significance Tests for Machine Translation Evaluation - Koehn - 2004
81	Training Tree Transducers - Graehl, Knight, et al.
63	R.L.: The mathematics of statistical machine translation: Parameter estimation - Brown, Pietra, et al. - 1993
40	Head Automata and Bilingual Tiling: Translation with Minimal Representations - Alshawi - 1996
37	Testing Statistical Hypotheses (Second Edition - Lehmann - 1986
32	Syntax-based language models for statistical machine translation - Charniak, Knight, et al. - 2003
31	Loosely tree-based alignment for machine translation - Gildea - 2003
30	Statistical Phrase based Translation - Koehn, Och, et al. - 2003
21	Feature-rich statistical translation of noun phrases - Koehn, Knight - 2003
10	Parsing german with sister-head dependencies - Dubey, Keller - 2003