# An Exploration of Neural Sequence-to-Sequence Architectures for Automatic Post-Editing

arXiv: https://arxiv.org/abs/1706.04138 · HTML: https://mlsanity.com/paper/1706.04138/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jun 2017.

## Built on by (most cited first, 6 of 6)

- [Neural Machine Translation of Clinical Text: An Empirical Investigation into Multilingual Pre-Trained Language Models and Transfer-Learning](https://mlsanity.com/paper/2312.07250/) (2023)
- [Giving the Old a Fresh Spin: Quality Estimation-Assisted Constrained Decoding for Automatic Post-Editing](https://mlsanity.com/paper/2501.17265/) (2025)
- [Computational Morphology with Neural Network Approaches](https://mlsanity.com/paper/2105.09404/) (2021)
- [PePe: Personalized Post-editing Model utilizing User-generated Post-edits](https://mlsanity.com/paper/2209.10139/) (2022)
- [Action based Network for Conversation Question Reformulation](https://mlsanity.com/paper/2111.14445/) (2021)
- [An Empirical Study of Automatic Post-Editing](https://mlsanity.com/paper/2209.07759/) (2022)

## Abstract (arXiv)

In this work, we explore multiple neural architectures adapted for the task of automatic post-editing of machine translation output. We focus on neural end-to-end models that combine both inputs mt (raw MT output) and src (source language input) in a single neural architecture, modeling mt, src rightarrow pe directly. Apart from that, we investigate the influence of hard-attention models which seem to be well-suited for monolingual tasks, as well as combinations of both ideas. We report results on data sets provided during the WMT-2016 shared task on automatic post-editing and can demonstrate that dual-attention models that incorporate all available data in the APE scenario in a single model improve on the best shared task system and on all other published results after the shared task. Dual-attention models that are combined with hard attention remain competitive despite applying fewer changes to the input.