Analysis, statistical transfer, and synthesis in machine translation

Abstract

We reinterpret the system described by Brown et al. [1] in terms of the analysis-transfer-synthesis paradigm common in machine translation. We describe enhanced analysis and synthesis components that apply a number of simple linguistic transformations so the transfer component operates from a string of French morphemes to a string of English morphemes. We report the results of a comparison of the new system with the old system on 100 short test sentences. The new system correctly translates 60 % of these sentences while the old system correctly translates only 39 % of them.