mlsanityData to 7 Oct 2026

Synthetic and Natural Noise Both Break Neural Machine Translation

arXiv 1711.02173 ↗First posted 6 Nov 2017cs.CL cs.LGcited by 304

Not on the map. Why?

Abstract (arXiv)

Character-based neural machine translation (NMT) models alleviate out-of-vocabulary issues, learn morphology, and move us closer to completely end-to-end translation systems. Unfortunately, they are also very brittle and easily falter when presented with noisy data. In this paper, we confront NMT models with synthetic and natural sources of noise. We find that state-of-the-art models fail to translate even moderately noisy texts that humans have no trouble comprehending. We explore two approaches to increase model robustness: structure-invariant word representations and robust training on noisy texts. We find that a model based on a character convolutional neural network is able to simultaneously learn representations robust to multiple kinds of noise.

Key facts. Cited by 304 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 89; 2022: 54; 2023: 67; 2024: 43; 2025: 26; 2026: 25.

304 papers.

Sort:

By area:

  1. 2021Datasets: A Community Library for Natural Language Processingcited by 526
  2. 2021Dynabench: Rethinking Benchmarking in NLPcited by 447
  3. 2021XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languagescited by 346
  4. 2023Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attackscited by 189
  5. 2023Do LLMs exhibit human-like response biases? A case study in survey designcited by 176
  6. 2021Charformer: Fast Character Transformers via Gradient-based Subword Tokenizationcited by 158
  7. 2021Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfercited by 147
  8. 2021MultiBench: Multiscale Benchmarks for Multimodal Representation Learningcited by 143
  9. 2023AugGPT: Leveraging ChatGPT for Text Data Augmentationcited by 128
  10. 2021A Survey on Data Augmentation for Text Classificationcited by 111
  11. 2021Robustness Gym: Unifying the NLP Evaluation Landscapecited by 107
  12. 2021Measure and Improve Robustness in NLP Models: A Surveycited by 107
38 more
  1. 2021An Empirical Survey of Data Augmentation for Limited Data Learning in NLPcited by 101
  2. 2023Waffling around for Performance: Visual Classification with Random Words and Broad Conceptscited by 100
  3. 2023A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validationcited by 91
  4. 2021Evaluating the Robustness of Neural Language Models to Input Perturbationscited by 87
  5. 2021Leveraging Automated Unit Tests for Unsupervised Code Translationcited by 82
  6. 2021Bad Characters: Imperceptible NLP Attackscited by 69
  7. 2024LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancementcited by 69
  8. 2021Towards Robustness Against Natural Language Word Substitutionscited by 68
  9. 2025Dynamic Chunking for End-to-End Hierarchical Sequence Modelingcited by 65
  10. 2021CLINE: Contrastive Learning with Semantic Negative Examples for Natural Language Understandingcited by 50
  11. 2021How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?cited by 49
  12. 2021Robust Open-Vocabulary Translation from Visual Text Representationscited by 47
  13. 2022VALUE: Understanding Dialect Disparity in NLUcited by 45
  14. 2023On Robustness of Prompt-based Semantic Parsing with Large Pre-trained Language Model: An Empirical Study on Codexcited by 41
  15. 2024Changing Answer Order Can Decrease MMLU Accuracycited by 41
  16. 2022Order-Disorder: Imitation Adversarial Attacks for Black-box Neural Ranking Modelscited by 37
  17. 2022Can Rationalization Improve Robustness?cited by 36
  18. 2023In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPTcited by 35
  19. 2021On Compositional Generalization of Neural Machine Translationcited by 34
  20. 2021SGD-X: A Benchmark for Robust Generalization in Schema-Guided Dialogue Systemscited by 34
  21. 2021Towards Robust Classification Model by Counterfactual and Invariant Data Generationcited by 30
  22. 2021Challenges in Generalization in Open Domain Question Answeringcited by 30
  23. 2023Large Language Models for Healthcare Data Augmentation: An Example on Patient-Trial Matchingcited by 30
  24. 2023Don't blame Dataset Shift! Shortcut Learning due to Gradients and Cross Entropycited by 30
  25. 2023The Trickle-down Impact of Reward (In-)consistency on RLHFcited by 29
  26. 2022Towards Robustness of Text-to-SQL Models Against Natural and Realistic Adversarial Table Perturbationcited by 28
  27. 2023Assessing Hidden Risks of LLMs: An Empirical Study on Robustness, Consistency, and Credibilitycited by 28
  28. 2022Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methodscited by 27
  29. 2023Dissociating language and thought in large language modelscited by 27
  30. 2021Substructure Substitution: Structured Data Augmentation for NLPcited by 25
  31. 2021NoiseQA: Challenge Set Evaluation for User-Centric Question Answeringcited by 25
  32. 2021Reliability Testing for Natural Language Processing Systemscited by 25
  33. 2025reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputscited by 25
  34. 2021Data Augmentation in Natural Language Processing: A Novel Text Generation Approach for Long and Short Text Classifierscited by 24
  35. 2021How Robust are Model Rankings: A Leaderboard Customization Approach for Equitable Evaluationcited by 24
  36. 2024On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMscited by 24
  37. 2022Phrase-level Textual Adversarial Attack with Label Preservationcited by 23
  38. 2022Certified Robustness Against Natural Language Attacks by Causal Interventioncited by 23

50 most cited of 304 All 304 (JSON)