Abstract
Preceding a phrase-based statistical machine translation (PSMT) system by a
syntactically-informed reordering preprocessing step has been shown to improve
overall translation performance compared to a baseline PSMT system. However, the
improvement is not seen for every sentence. We use a lattice input to a PSMT
system in order to translate simultaneously across both original and reordered versions of a sentence, and include a number of confidence features to support the system in choosing on a sentence-by-sentence basis whether to use the reordering process. In German-to-English translation, our best system achieves a BLEU score of
21.39, an improvement of 0.62.
Original language | English |
---|---|
Pages (from-to) | 32-40 |
Number of pages | 9 |
Journal | Proceedings of the Australasian Language Technology Association Workshop 2010 |
Publication status | Published - 2010 |
Event | Australasian Language Technology Association Workshop - Melbourne Duration: 9 Dec 2010 → 10 Dec 2010 |