# Neural Machine Translation of Text from Non-Native Speakers

arXiv: https://arxiv.org/abs/1808.06267 · HTML: https://mlsanity.com/paper/1808.06267/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Aug 2018.

## Built on by (most cited first, 10 of 10)

- [Measure and Improve Robustness in NLP Models: A Survey](https://mlsanity.com/paper/2112.08313/) (2021)
- [Improving Zero-shot Cross-lingual Transfer between Closely Related Languages by injecting Character-level Noise](https://mlsanity.com/paper/2109.06772/) (2021)
- [Data Augmentation by Concatenation for Low-Resource Translation: A Mystery and a Solution](https://mlsanity.com/paper/2105.01691/) (2021)
- [Autocorrect in the Process of Translation -- Multi-task Learning Improves Dialogue Machine Translation](https://mlsanity.com/paper/2103.16189/) (2021)
- [Visual Cues and Error Correction for Translation Robustness](https://mlsanity.com/paper/2103.07352/) (2021)
- [DialUp! Modeling the Language Continuum by Adapting Models to Dialects and Dialects to Models](https://mlsanity.com/paper/2501.16581/) (2025)
- [A Representation Level Analysis of NMT Model Robustness to Grammatical Errors](https://mlsanity.com/paper/2505.21224/) (2025)
- [Why Robust Natural Language Understanding is a Challenge](https://mlsanity.com/paper/2206.14575/) (2022)
- [Toward Machine Interpreting: Lessons from Human Interpreting Studies](https://mlsanity.com/paper/2508.07964/) (2025)
- [Cross-Modal Robustness Transfer (CMRT): Training Robust Speech Translation Models Using Adversarial Text](https://mlsanity.com/paper/2602.11933/) (2026)

## Abstract (arXiv)

Neural Machine Translation (NMT) systems are known to degrade when confronted with noisy data, especially when the system is trained only on clean data. In this paper, we show that augmenting training data with sentences containing artificially-introduced grammatical errors can make the system more robust to such errors. In combination with an automatic grammar error correction system, we can recover 1.5 BLEU out of 2.4 BLEU lost due to grammatical errors. We also present a set of Spanish translations of the JFLEG grammar error correction corpus, which allows for testing NMT robustness to real grammatical errors.