# Towards Robust Neural Machine Translation

arXiv: https://arxiv.org/abs/1805.06130 · HTML: https://mlsanity.com/paper/1805.06130/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 May 2018.

## Built on by (most cited first, 30 of 35)

- [Waffling around for Performance: Visual Classification with Random Words and Broad Concepts](https://mlsanity.com/paper/2306.07282/) (2023)
- [STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation](https://mlsanity.com/paper/2203.10426/) (2022)
- [Learning Shared Semantic Space for Speech-to-Text Translation](https://mlsanity.com/paper/2105.03095/) (2021)
- [On Compositional Generalization of Neural Machine Translation](https://mlsanity.com/paper/2105.14802/) (2021)
- [Disentangled Sequence to Sequence Learning for Compositional Generalization](https://mlsanity.com/paper/2110.04655/) (2021)
- [Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods](https://mlsanity.com/paper/2203.05227/) (2022)
- [Putting words into the system's mouth: A targeted attack on neural machine translation using monolingual data poisoning](https://mlsanity.com/paper/2107.05243/) (2021)
- [Regularizing End-to-End Speech Translation with Triangular Decomposition Agreement](https://mlsanity.com/paper/2112.10991/) (2021)
- [Towards Robust k-Nearest-Neighbor Machine Translation](https://mlsanity.com/paper/2210.08808/) (2022)
- [Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translation](https://mlsanity.com/paper/2204.06812/) (2022)
- [TransFool: An Adversarial Attack against Neural Machine Translation Models](https://mlsanity.com/paper/2302.00944/) (2023)
- [Improving the Robustness of Summarization Systems with Dual Augmentation](https://mlsanity.com/paper/2306.01090/) (2023)
- [Autocorrect in the Process of Translation -- Multi-task Learning Improves Dialogue Machine Translation](https://mlsanity.com/paper/2103.16189/) (2021)
- [Neural Machine Translation for the Indigenous Languages of the Americas: An Introduction](https://mlsanity.com/paper/2306.06804/) (2023)
- [Addressing the Vulnerability of NMT in Input Perturbations](https://mlsanity.com/paper/2104.09810/) (2021)
- [Adversarial Training with Contrastive Learning in NLP](https://mlsanity.com/paper/2109.09075/) (2021)
- [Noisy Exemplars Make Large Language Models More Robust: A Domain-Agnostic Behavioral Analysis](https://mlsanity.com/paper/2311.00258/) (2023)
- [Synthetic Data Generation and Joint Learning for Robust Code-Mixed Translation](https://mlsanity.com/paper/2403.16771/) (2024)
- [Simple Contrastive Representation Adversarial Learning for NLP Tasks](https://mlsanity.com/paper/2111.13301/) (2021)
- [Generating Authentic Adversarial Examples beyond Meaning-preserving with Doubly Round-trip Translation](https://mlsanity.com/paper/2204.08689/) (2022)
- [AdMix: A Mixed Sample Data Augmentation Method for Neural Machine Translation](https://mlsanity.com/paper/2205.04686/) (2022)
- [Sometimes We Want Translationese](https://mlsanity.com/paper/2104.07623/) (2021)
- [Checks and Strategies for Enabling Code-Switched Machine Translation](https://mlsanity.com/paper/2210.05096/) (2022)
- [Visual Cues and Error Correction for Translation Robustness](https://mlsanity.com/paper/2103.07352/) (2021)
- [PAEG: Phrase-level Adversarial Example Generation for Neural Machine Translation](https://mlsanity.com/paper/2201.02009/) (2022)
- [Categorizing Semantic Representations for Neural Machine Translation](https://mlsanity.com/paper/2210.06709/) (2022)
- [Layer-wise Representation Fusion for Compositional Generalization](https://mlsanity.com/paper/2307.10799/) (2023)
- [Impact of Visual Context on Noisy Multimodal NMT: An Empirical Study for English to Indian Languages](https://mlsanity.com/paper/2308.16075/) (2023)
- [TF-Attack: Transferable and Fast Adversarial Attacks on Large Language Models](https://mlsanity.com/paper/2408.13985/) (2024)
- [A Discussion on Building Practical NLP Leaderboards: The Case of Machine Translation](https://mlsanity.com/paper/2106.06292/) (2021)

## Abstract (arXiv)

Small perturbations in the input can severely distort intermediate representations and thus impact translation quality of neural machine translation (NMT) models. In this paper, we propose to improve the robustness of NMT models with adversarial stability training. The basic idea is to make both the encoder and decoder in NMT models robust against input perturbations by enabling them to behave similarly for the original input and its perturbed counterpart. Experimental results on Chinese-English, English-German and English-French translation tasks show that our approaches can not only achieve significant improvements over strong NMT systems but also improve the robustness of NMT models.