BLEU: a method for automatic evaluation of machine translation
ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Coarse-to-fine n-best parsing and MaxEnt discriminative reranking
ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Clause restructuring for statistical machine translation
ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
On the impact of morphology in English to Spanish statistical MT
Speech Communication
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
Using a dependency parser to improve SMT for subject-object-verb languages
NAACL '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics
A POS-based model for long-range reorderings in SMT
StatMT '09 Proceedings of the Fourth Workshop on Statistical Machine Translation
Automatically learning source-side reordering rules for large scale machine translation
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics
Training a parser for machine translation reordering
EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Hi-index | 0.00 |
When translating English to German, existing reordering models often cannot model the long-range reorderings needed to generate German translations with verbs in the correct position. We reorder English as a preprocessing step for English-to-German SMT. We use a sequence of hand-crafted reordering rules applied to English parse trees. The reordering rules place English verbal elements in the positions within the clause they will have in the German translation. This is a difficult problem, as German verbal elements can appear in different positions within a clause (in contrast with English verbal elements, whose positions do not vary as much). We obtain a significant improvement in translation performance.