Shterionov, D., Félix do Carmo, F., Moorkens, J., Hossari, M., Wagner, J., Paquin, E., Schmidtke, D.,Groves, D., Way, A.

2020

September

Machine Translation

A Roadmap to Neural Automatic Post-Editing – an Empirical Approach

Published

()

Automatic post-editing, Neural post-editing, Multi-source, Deep learning, Empirical evaluation, Machine Translation

34

2

In a translation workflow, machine translation (MT) is almost always followed by a human post-editing step, where the raw MT output is corrected to meet required quality standards. To reduce the number of errors human translators need to correct, automatic post-editing (APE) methods have been developed and deployed in such workflows. With the advances in deep learning, neural APE (NPE) systems have outranked more traditional, statistical, ones. However, the plethora of options, variables and settings, as well as the relation between NPE performance and train/test data makes it difficult to select the most suitable approach for a given use case.

Berlin

0922-6567

https://link.springer.com/article/10.1007%2Fs10590-020-09249-7

10.1007/s10590-020-09249-7