Undirected Machine Translation with Discriminative Reinforcement Learning

We present a novel Undirected Machine Translation model of Hierarchical MT that is not constrained to the standard bottomup inference order. Removing the ordering constraint makes it possible to condition on top-down structure and surrounding context. This allows the introduction of a new class of contextual features that are not constrained to condition only on the bottom-up context. The model builds translation-derivations efficiently in a greedy fashion. It is trained to learn to choose jointly the best action and the best inference order. Experiments show that the decoding time is halved and forestrescoring is 6 times faster, while reaching accuracy not significantly different from state of the art.