# Can Automatic Post-Editing Improve NMT?

arXiv: https://arxiv.org/abs/2009.14395 · HTML: https://mlsanity.com/paper/2009.14395/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Sep 2020.

## Built on by (most cited first, 17 of 17)

- [Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey](https://mlsanity.com/paper/2210.07700/) (2022)
- [Leveraging GPT-4 for Automatic Translation Post-Editing](https://mlsanity.com/paper/2305.14878/) (2023)
- [TEaR: Improving LLM-based Machine Translation with Systematic Self-Refinement](https://mlsanity.com/paper/2402.16379/) (2024)
- [Iterative Translation Refinement with Large Language Models](https://mlsanity.com/paper/2306.03856/) (2023)
- [Ladder: A Model-Agnostic Framework Boosting LLM-based Machine Translation to the Next Level](https://mlsanity.com/paper/2406.15741/) (2024)
- [Lost in Translationese? Reducing Translation Effect Using Abstract Meaning Representation](https://mlsanity.com/paper/2304.11501/) (2023)
- [Beyond Decoder-only: Large Language Models Can be Good Encoders for Machine Translation](https://mlsanity.com/paper/2503.06594/) (2025)
- [Reference Matters: Benchmarking Factual Error Correction for Dialogue Summarization with Fine-grained Evaluation Framework](https://mlsanity.com/paper/2306.05119/) (2023)
- [Learning to Combine Instructions in LLVM Compiler](https://mlsanity.com/paper/2202.12379/) (2022)
- [RoundTripOCR: A Data Generation Technique for Enhancing Post-OCR Error Correction in Low-Resource Devanagari Languages](https://mlsanity.com/paper/2412.15248/) (2024)
- [Automatic Correction of Human Translations](https://mlsanity.com/paper/2206.08593/) (2022)
- [Repairing Pronouns in Translation with BERT-Based Post-Editing](https://mlsanity.com/paper/2103.12838/) (2021)
- [An Empirical Study of Automatic Post-Editing](https://mlsanity.com/paper/2209.07759/) (2022)
- [TegFormer: Topic-to-Essay Generation with Good Topic Coverage and High Text Coherence](https://mlsanity.com/paper/2212.13456/) (2022)
- [LangMark: A Multilingual Dataset for Automatic Post-Editing](https://mlsanity.com/paper/2511.17153/) (2025)
- [APEX-VW: A Document-Level English-Spanish Post-Editing Dataset in the Healthcare Domain](https://mlsanity.com/paper/2608.08059/) (2026)
- [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) aims to improve machine translations, thereby reducing human post-editing effort. APE has had notable success when used with statistical machine translation (SMT) systems but has not been as successful over neural machine translation (NMT) systems. This has raised questions on the relevance of APE task in the current scenario. However, the training of APE models has been heavily reliant on large-scale artificial corpora combined with only limited human post-edited data. We hypothesize that APE models have been underperforming in improving NMT translations due to the lack of adequate supervision. To ascertain our hypothesis, we compile a larger corpus of human post-edits of English to German NMT. We empirically show that a state-of-art neural APE model trained on this corpus can significantly improve a strong in-domain NMT system, challenging the current understanding in the field. We further investigate the effects of varying training data sizes, using artificial training data, and domain specificity for the APE task. We release this new corpus under CC BY-NC-SA 4.0 license at https://github.com/shamilcm/pedra.