Abstract
We propose a pre-reordering scheme to improve the quality of machine translation by permuting the words of a source sentence to a target-like order. This is accomplished as a transition-based system that walks on the dependency parse tree of the sentence and emits words in target-like order, driven by a classifier trained on a parallel corpus. Our system is capable of generating arbitrary permutations up to flexible constraints determined by the choice of the classifier algorithm and input features.
Original language | English |
---|---|
Title of host publication | Proceedings of the Eighth Workshop on Statistical Machine Translation |
Publisher | Association for Computational Linguistics (ACL) |
Pages | 164-169 |
Number of pages | 6 |
Publication status | Published - 2013 |
Event | ACl 2013 Eighth Workshop on Statistical Machine Translation - Sofia, Bulgaria Duration: 8 Aug 2013 → 9 Aug 2013 http://www.statmt.org/wmt13/ |
Workshop
Workshop | ACl 2013 Eighth Workshop on Statistical Machine Translation |
---|---|
Abbreviated title | WMT13 |
Country/Territory | Bulgaria |
City | Sofia |
Period | 8/08/13 → 9/08/13 |
Internet address |