Algorithms for Syntax-Aware Statistical Machine Translation

All of the non-trivial algorithms that are necessary for building and applying a rudimentary syntax-aware statistical machine translation system are generalized parsers. This paper extends the “translation by parsing” architecture by adding two components that are invariably used by state-of-the-art statistical machine translation systems. First, the paper shows how a generic syntax-aware translation algorithm can accommodate independently estimated -gram language models. Second, the paper introduces an automatic MT evaluation method that accounts for meaning-preserving syntactic alternations. The core algorithms in both extensions are, again, generalized parsers.