Optimizing Machine Translation by Learning to Search

Abstract

We present a novel approach to training discriminative tree-structured machine trans- lation systems by learning to search. We describe three primary innovations in this work: a new parsing coordinator architecture and algorithms to generate the required training examples for the learning algorithm; a new semiring that provides an unbiased way to compare translations; and a new training objective that measures whether a translation inference improves the quality of a translation. We also apply the reinforcement learning concept of exploration to SMT. Finally, we empirically evaluate our innovations.