Online Automatic Post-Editing across Domains

Recent advances in automatic post-editing (APE) have shown that it is possible to automatically correct system-atic errors made by machine translation systems. However, most of the current APE techniques have only been tested in controlled batch environments, where training and test data are sampled from the same distribution and the training set is fully available. In this paper, we propose an online APE system based on an instance selection mechanism that is able to efficiently work with a stream of data points belonging to different domains. Our results on a mix of two datasets show that our system is able to: i)outperform state-of-the-art online APE solutions and ii) significantly improve the quality of rough MToutput.