Syntax-aware Phrase-based Statistical Machine Translation: System Description.

We present a variant of phrase-based SMT that uses source-side parsing and a constituent reordering model based on word alignments in the word-aligned training corpus to predict hierarchical block-wise reordering of the input. Multiple possible translation orders are represented compactly in a source order lattice. This source order lattice is then annotated with phrase-level translations to form a lattice of tokens in the target language. Various feature functions are combined in a log-linear fashion to evaluate paths through that lattice.