Aligning through divergence
Johan Segura, Violaine Prince · 2012
Abstract—This document presents a bilingual phrase-based alignment method handling syntactic constituents (sub-sentential components) of parallel sentences. The method rely on an asymmetrical parsing of both languages: Light part-of-speech tagging for the target language, syntactic tree building for the ’source ’ language and the complexity of each is studied. The models and methods can be seen as a subclass of Example Based Machine Translation. I.