Abstract

We investigate the impact of parse quality on a syntactically-informed statistical machine translation system applied to technical text. We vary parse quality by varying the amount of data used to train the parser. As the amount of data increases, parse quality improves, leading to improvements in machine translation output and results that significantly outperform a state-of-the-art phrasal baseline.

Citations

992	BLEU: A Method for Automatic Evaluation of Machine Translation - Papineni, Roukos, et al. - 2002
341	Improved statistical alignment models - Och, Ney - 2000
296	Dependency Syntax: Theory and Practice - Melcuk - 1988
282	Lattice-based minimum error rate training for statistical machine translation - Macherey, Och, et al. - 2008
200	Three New Probabilistic Models for Dependency Parsing: An Exploration - Eisner - 1996
181	Feature-rich part-of-speech tagging with a cyclic dependency network - Toutanova, Klein, et al. - 2003
145	Eleménts de syntaxe structurale - Tesniére - 1959
102	Dependency treelet translation: Syntactically informed phrasal smt - Quirk, Menezes, et al. - 2005
93	phrase-based translation - Statistical
83	Statistical dependency analysis with support vector machines - Yamada, Matsumoto - 2003
55	Bayes point machines - Herbrich, Graepel, et al. - 2001
40	A Bit of Progress in Language Modeling, Extended Version. Microsoft Research - Goodman - 2001
8	Normalizing German and English inflectional morphology to improve statistical word alignment. Machine Translation: From Real Users to Research - Corston-Oliver, Gamon - 2004
6	Eric Ringger. 2006. Multilingual dependency parsing using Bayes Point Machines - Corston-Oliver, Aue, et al.
6	Point Machines - Bayes
5	Extraposition: A case study in German sentence realization - Gamon, Ringger, et al. - 2002