# MS-UEdin Submission to the WMT2018 APE Shared Task: Dual-Source Transformer for Automatic Post-Editing

arXiv: https://arxiv.org/abs/1809.00188 · HTML: https://mlsanity.com/paper/1809.00188/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Sep 2018.

## Built on by (most cited first, 13 of 13)

- [Iterative Translation Refinement with Large Language Models](https://mlsanity.com/paper/2306.03856/) (2023)
- [Focused Attention Improves Document-Grounded Generation](https://mlsanity.com/paper/2104.12714/) (2021)
- [WeTS: A Benchmark for Translation Suggestion](https://mlsanity.com/paper/2110.05151/) (2021)
- [Integrating Translation Memories into Non-Autoregressive Machine Translation](https://mlsanity.com/paper/2210.06020/) (2022)
- [Towards Personalised and Document-level Machine Translation of Dialogue](https://mlsanity.com/paper/2102.10979/) (2021)
- [Transfer Learning for Sequence Generation: from Single-source to Multi-source](https://mlsanity.com/paper/2105.14809/) (2021)
- [Bilingual Synchronization: Restoring Translational Relationships with Editing Operations](https://mlsanity.com/paper/2210.13163/) (2022)
- [Revisiting Context Choices for Context-aware Machine Translation](https://mlsanity.com/paper/2109.02995/) (2021)
- [PePe: Personalized Post-editing Model utilizing User-generated Post-edits](https://mlsanity.com/paper/2209.10139/) (2022)
- [A Case Study on Context Encoding in Multi-Encoder based Document-Level Neural Machine Translation](https://mlsanity.com/paper/2308.06063/) (2023)
- [An Empirical Study of Automatic Post-Editing](https://mlsanity.com/paper/2209.07759/) (2022)
- [LangMark: A Multilingual Dataset for Automatic Post-Editing](https://mlsanity.com/paper/2511.17153/) (2025)
- [Confident but Wrong: A Constrained Decoding Diagnostic for Low-Resource Automatic Post-Editing](https://mlsanity.com/paper/2609.29680/) (2026)

## Abstract (arXiv)

This paper describes the Microsoft and University of Edinburgh submission to the Automatic Post-editing shared task at WMT2018. Based on training data and systems from the WMT2017 shared task, we re-implement our own models from the last shared task and introduce improvements based on extensive parameter sharing. Next we experiment with our implementation of dual-source transformer models and data selection for the IT domain. Our submissions decisively wins the SMT post-editing sub-task establishing the new state-of-the-art and is a very close second (or equal, 16.46 vs 16.50 TER) in the NMT sub-task. Based on the rather weak results in the NMT sub-task, we hypothesize that neural-on-neural APE might not be actually useful.