Can Markov Models Over Minimal Translation Units Help Phrase-Based SMT?
Nadir Durrani, Alexander Fraser, Helmut Schmid, Hieu Hoang and Philipp Koehn
The 51st Annual Meeting of the Association for Computational Linguistics - Short Papers (ACL Short Papers 2013)
Sofia, Bulgaria, August 4-9, 2013
The phrase-based and N-gram-based SMT approaches complement each other in terms of their pros and cons. 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.
Conference Manager (V2.61.0 - Rev. 2792M)