Context-free reordering, finite-state translation

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 comparable hierarchical phrase-based transla-tion model.