Can Markov Models Over Minimal Translation Units Help Phrase-Based SMT?

Nadir Durrani, Alexander Fraser, Helmut Schmid, Hieu Hoang, Philipp Koehn

The phrase-based and N-gram-based SMT frameworks complement each
other. While the former has a better ability to memorize, the latter
provides a more principled model that captures dependencies across
phrasal boundaries.  Some work has been done to combine insights from
these frameworks. A recent successful attempt showed the advantage of
using phrase-based search on top of an N-gram-based model.  We probe
this question in the reverse direction by investigating whether
integrating N-gram-based translation and reordering models into a
phrase-based decoder helps overcome the problematic phrasal
independence assumption. A large scale evaluation over 8 language
pairs shows that performance does significantly improve.