Learning to Copy for Automatic Post-Editing
This work addresses a specific challenge in automatic post-editing for natural language processing, offering an incremental improvement over existing neural network methods.
The paper tackles the problem of modeling copying mechanisms in automatic post-editing for machine translation by proposing a method that learns interactive representations of source sentences and system outputs to identify errors, resulting in outperforming all best published results on WMT 2016-2017 datasets.
Automatic post-editing (APE), which aims to correct errors in the output of machine translation systems in a post-processing step, is an important task in natural language processing. While recent work has achieved considerable performance gains by using neural networks, how to model the copying mechanism for APE remains a challenge. In this work, we propose a new method for modeling copying for APE. To better identify translation errors, our method learns the representations of source sentences and system outputs in an interactive way. These representations are used to explicitly indicate which words in the system outputs should be copied, which is useful to help CopyNet (Gu et al., 2016) better generate post-edited translations. Experiments on the datasets of the WMT 2016-2017 APE shared tasks show that our approach outperforms all best published results.