Multi-source Transformer for Automatic Post-Editing

Recent approaches to the Automatic Post-editing (APE) of Machine Translation (MT) have shown that best results are obtained by neural multi-source models that correct the raw MT output by also considering information from the corresponding source sentence. In this paper, we pursue this objective by exploiting, for the first time in APE, the Transformerarchitecture. Our approach is much simpler than the best current solutions, which are based on ensembling multiple models and adding a final hypothesis reranking step. We evaluate our Transformer-based system on the English-German data released for the WMT 2017 APE shared task, achieving results that outperform the state of the art with a simpler architecture suitable for industrial applications.