MT based on Probabilistic Synchronous Dependency Insertion Grammar (PSDIG)

This proposal is an extension to the project “Generation in the Context of Machine Translation”, which is one of the projects done in the Johns Hopkins University Center for Speech and Language Processing 2002 summer workshop (WS02GMT). We first address some issues observed in WS02GMT which possibly leads to detrimental effects in machine translation performance. And hence we propose a new approach to construct the syntax based machine translation pipeline. Our proposal consists of two parts: first, doing machine translation based on shallow syntax level (roughly AR) instead deep syntax level (TR); and second, constructing a Probabilistic Synchronous Dependency Insertion Grammar (PSDIG) before constructing the machine translation model.