Extending Phrase-based Decoding with a Dependency-based Reordering Model

Phrase-based decoding is conceptually simple and straightforward to implement, at the cost of drasti-cally oversimplified reordering models. Syntactically aware models make it possible to capture linguisti-cally relevant relationships in order to improve word order, but they can be more complex to implement and optimise. In this paper, we explore a new middle ground between phrase-based and syntactically informed statistical MT, in the form of a model that supplements conventional, non-hierarchical phrase-based techniques with linguistically informed reordering based on syntactic dependency trees. The key idea is to exploit linguistically-informed hierchical structures only for those dependencies that cannot be captured within a single flat phrase. For very local dependencies we leverage the success of conventional phrase-based approaches, which provide a sequence of target-language words appropriately ordered and ready-made with the appropriate agreement morphology. Working with dependency trees rather than constituency trees allows us to take advantage of the flexi-bility of phrase-based systems to treat non-constituent fragments as phrases. We do impose a requirement — that the fragment be a novel sort of “dependency constituent ” — on what can be translated as a phrase, but this is much weaker than the requirement that phrases be traditional linguistic constituents, which has often proven too restrictive in MT systems.