Iterative Refinement for Machine Translation
This addresses the issue of error propagation in machine translation for users of translation systems, though it is incremental as it builds on existing methods.
The paper tackles the problem of irreversible errors in machine translation by introducing an iterative refinement scheme that allows revisiting previous decisions, improving phrase-based translation by up to 0.4 BLEU on WMT15 German-English.
Existing machine translation decoding algorithms generate translations in a strictly monotonic fashion and never revisit previous decisions. As a result, earlier mistakes cannot be corrected at a later stage. In this paper, we present a translation scheme that starts from an initial guess and then makes iterative improvements that may revisit previous decisions. We parameterize our model as a convolutional neural network that predicts discrete substitutions to an existing translation based on an attention mechanism over both the source sentence as well as the current translation output. By making less than one modification per sentence, we improve the output of a phrase-based translation system by up to 0.4 BLEU on WMT15 German-English translation.