mlsanityData to 7 Oct 2026

Towards Robust Neural Machine Translation

arXiv 1805.06130 ↗First posted 16 May 2018cs.CLcited by 35

Not on the map. Why?

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.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 10; 2023: 8; 2024: 3; 2025: 0; 2026: 1.

35 papers.

Sort:

By area:

  1. 2023Waffling around for Performance: Visual Classification with Random Words and Broad Conceptscited by 100
  2. 2022STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translationcited by 57
  3. 2021Learning Shared Semantic Space for Speech-to-Text Translationcited by 49
  4. 2021On Compositional Generalization of Neural Machine Translationcited by 34
  5. 2021Disentangled Sequence to Sequence Learning for Compositional Generalizationcited by 30
  6. 2022Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methodscited by 27
  7. 2021Putting words into the system's mouth: A targeted attack on neural machine translation using monolingual data poisoningcited by 19
  8. 2021Regularizing End-to-End Speech Translation with Triangular Decomposition Agreementcited by 16
  9. 2022Towards Robust k-Nearest-Neighbor Machine Translationcited by 15
  10. 2022Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translationcited by 13
  11. 2023TransFool: An Adversarial Attack against Neural Machine Translation Modelscited by 12
  12. 2023Improving the Robustness of Summarization Systems with Dual Augmentationcited by 9
23 more
  1. 2021Autocorrect in the Process of Translation -- Multi-task Learning Improves Dialogue Machine Translationcited by 8
  2. 2023Neural Machine Translation for the Indigenous Languages of the Americas: An Introductioncited by 7
  3. 2021Addressing the Vulnerability of NMT in Input Perturbationscited by 6
  4. 2021Adversarial Training with Contrastive Learning in NLPcited by 6
  5. 2023Noisy Exemplars Make Large Language Models More Robust: A Domain-Agnostic Behavioral Analysiscited by 6
  6. 2024Synthetic Data Generation and Joint Learning for Robust Code-Mixed Translationcited by 5
  7. 2021Simple Contrastive Representation Adversarial Learning for NLP Taskscited by 4
  8. 2022Generating Authentic Adversarial Examples beyond Meaning-preserving with Doubly Round-trip Translationcited by 4
  9. 2022AdMix: A Mixed Sample Data Augmentation Method for Neural Machine Translationcited by 4
  10. 2021Sometimes We Want Translationesecited by 3
  11. 2022Checks and Strategies for Enabling Code-Switched Machine Translationcited by 3
  12. 2021Visual Cues and Error Correction for Translation Robustnesscited by 2
  13. 2022PAEG: Phrase-level Adversarial Example Generation for Neural Machine Translationcited by 2
  14. 2022Categorizing Semantic Representations for Neural Machine Translationcited by 2
  15. 2023Layer-wise Representation Fusion for Compositional Generalizationcited by 2
  16. 2023Impact of Visual Context on Noisy Multimodal NMT: An Empirical Study for English to Indian Languagescited by 2
  17. 2021A Discussion on Building Practical NLP Leaderboards: The Case of Machine Translationcited by 1
  18. 2024Learning Robust Named Entity Recognizers From Noisy Data With Retrieval Augmentationcited by 1
  19. 2024TF-Attack: Transferable and Fast Adversarial Attacks on Large Language Modelscited by 1
  20. 2021Masked Adversarial Generation for Neural Machine Translationcited by 0
  21. 2022Improving Lexical Embeddings for Robust Question Answeringcited by 0
  22. 2023Towards Reliable Neural Machine Translation with Consistency-Aware Meta-Learningcited by 0
  23. 2026PiDA: Phonetically-Informed Data Augmentation for Robust Vietnamese Speech Translationcited by 0