Learning to Copy for Automatic Post-Editing

TL;DR

This paper introduces a novel copying mechanism for automatic post-editing in machine translation, improving error correction by better modeling source and output representations, leading to state-of-the-art results.

Contribution

It proposes an interactive representation learning method to enhance copying in neural APE models, outperforming previous approaches.

Findings

Outperforms all previous published results on WMT 2016-2017 datasets.

Uses interactive source and output representations to improve copying accuracy.

Enhances CopyNet with explicit copying indicators.

Abstract

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.