Paper: Context-free reordering finite-state translation

ACL ID N10-1128
Title Context-free reordering finite-state translation
Venue Human Language Technologies
Session Main Conference
Year 2010

We describe a class of translation model in which a set of input variants encoded as a context-free forest is translated using a finite- state translation model. The forest structure of the input is well-suited to representing word order alternatives, making it straightforward to model translation as a two step process: (1) tree-based source reordering and (2) phrase transduction. By treating the reordering pro- cess as a latent variable in a probabilistic trans- lation model, we can learn a long-range source reordering model without example reordered sentences, which are problematic to construct. The resulting model has state-of-the-art trans- lation performance, uses linguistically moti- vated features to effectively model long range reordering, and is significantly smaller than a compar...