mlsanityData to 7 Oct 2026

How Robust Are Character-Based Word Embeddings in Tagging and MT Against Wrod Scramlbing or Randdm Nouse?

arXiv 1704.04441 ↗First posted 14 Apr 2017cs.CLcited by 23

Not on the map. Why?

Abstract (arXiv)

This paper investigates the robustness of NLP against perturbed word forms. While neural approaches can achieve (almost) human-like accuracy for certain tasks and conditions, they often are sensitive to small changes in the input such as non-canonical input (e.g., typos). Yet both stability and robustness are desired properties in applications involving user-generated content, and the more as humans easily cope with such noisy or adversary conditions. In this paper, we study the impact of noisy input. We consider different noise distributions (one type of noise, combination of noise types) and mismatched noise distributions for training and testing. Moreover, we empirically evaluate the robustness of different models (convolutional neural networks, recurrent neural networks, non-neural models), different basic units (characters, byte pair encoding units), and different NLP tasks (morphological tagging, machine translation).

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 3; 2023: 6; 2024: 3; 2025: 3; 2026: 1.

23 papers.

Sort:

By area:

  1. 2023Waffling around for Performance: Visual Classification with Random Words and Broad Conceptscited by 100
  2. 2021Evaluating the Robustness of Neural Language Models to Input Perturbationscited by 87
  3. 2023Assessing Hidden Risks of LLMs: An Empirical Study on Robustness, Consistency, and Credibilitycited by 28
  4. 2021Improving Zero-shot Cross-lingual Transfer between Closely Related Languages by injecting Character-level Noisecited by 19
  5. 2023Make Every Example Count: On the Stability and Utility of Self-Influence for Learning from Noisy NLP Datasetscited by 18
  6. 2022PSSAT: A Perturbed Semantic Structure Awareness Transferring Method for Perturbation-Robust Slot Fillingcited by 9
  7. 2021Empirical Error Modeling Improves Robustness of Noisy Neural Sequence Labelingcited by 8
  8. 2021Understanding Model Robustness to User-generated Noisy Textscited by 8
  9. 2024Evaluating Large Language Models along Dimensions of Language Variation: A Systematik Invesdigatiom uv Cross-lingual Generalizationcited by 7
  10. 2022Systematicity, Compositionality and Transitivity of Deep NLP Models: a Metamorphic Testing Perspectivecited by 5
  11. 2023Towards Robust and Generalizable Training: An Empirical Study of Noisy Slot Filling for Input Perturbationscited by 5
  12. 2024Stochastic Monkeys at Play: Random Augmentations Cheaply Break LLM Safety Alignmentcited by 5
11 more
  1. 2021Integrating Approaches to Word Representationcited by 4
  2. 2023Enhancing Robustness of AI Offensive Code Generators via Data Augmentationcited by 3
  3. 2025Misspellings in Natural Language Processing: A surveycited by 3
  4. 2021Secoco: Self-Correcting Encoding for Neural Machine Translationcited by 2
  5. 2022Can NMT Understand Me? Towards Perturbation-based Evaluation of NMT Models for Code Generationcited by 2
  6. 2023CharSpan: Utilizing Lexical Similarity to Enable Zero-Shot Machine Translation for Extremely Low-resource Languagescited by 1
  7. 2024Interventional Speech Noise Injection for ASR Generalizable Spoken Language Understandingcited by 1
  8. 2025DialUp! Modeling the Language Continuum by Adapting Models to Dialects and Dialects to Modelscited by 1
  9. 2021AED: An black-box NLP classifier model attackercited by 0
  10. 2025Typoglycemia under the Hood: Investigating Language Models' Understanding of Scrambled Wordscited by 0
  11. 2026Towards a Diagnostic and Predictive Evaluation Methodology for Sequence Labeling Taskscited by 0