Transfer Machine Translation

A rule-based machine-translation paradigm that analyses the source text into a syntactic or semantic structure, applies a set of transfer rules to produce a corresponding structure in the target language, and then generates the target surface form. Transfer MT sits between direct MT and interlingual MT on the traditional MT pyramid: it handles more structural divergence than direct systems but is less ambitious — and less resource-hungry — than interlingual systems. In sign-language accessibility, transfer approaches can reorder English syntax toward ASL word order but cannot produce spatially rich phenomena such as classifier predicates, so they typically omit or approximate those constructions.