Online Learning for Neural Machine Translation Post-editing
This addresses the need for high-quality translations in tasks requiring post-editing, though it appears incremental as it builds on existing online learning methods.
The paper tackles the problem of improving neural machine translation systems by using online learning with post-edited translations as training data, resulting in significant improvements in translation quality and effort reduction.
Neural machine translation has meant a revolution of the field. Nevertheless, post-editing the outputs of the system is mandatory for tasks requiring high translation quality. Post-editing offers a unique opportunity for improving neural machine translation systems, using online learning techniques and treating the post-edited translations as new, fresh training data. We review classical learning methods and propose a new optimization algorithm. We thoroughly compare online learning algorithms in a post-editing scenario. Results show significant improvements in translation quality and effort reduction.