Iterative Refinement for Machine Translation

Understand

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.