# Learning to Copy for Automatic Post-Editing

arXiv: https://arxiv.org/abs/1911.03627 · HTML: https://mlsanity.com/paper/1911.03627/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Nov 2019.

## Built on by (most cited first, 4 of 4)

- [Transfer Learning for Sequence Generation: from Single-source to Multi-source](https://mlsanity.com/paper/2105.14809/) (2021)
- [PePe: Personalized Post-editing Model utilizing User-generated Post-edits](https://mlsanity.com/paper/2209.10139/) (2022)
- [An Empirical Study of Automatic Post-Editing](https://mlsanity.com/paper/2209.07759/) (2022)
- [Confident but Wrong: A Constrained Decoding Diagnostic for Low-Resource Automatic Post-Editing](https://mlsanity.com/paper/2609.29680/) (2026)

## Abstract (arXiv)

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.