Multi-rate HMMs for Word Alignment
Elif Eyigöz, Daniel Gildea, Kemal Oflazer · 2018
We apply multi-rate HMMs, a tree structured HMM model, to the word-alignment problem. Multi-rate HMMs allow us to model reordering at both the morpheme level and the word level in a hierarchical fashion. This approach leads to better machine translation results than a morpheme aware model that does not explicitly model morpheme reordering.