# It's Morphin' Time! Combating Linguistic Discrimination with Inflectional Perturbations

arXiv: https://arxiv.org/abs/2005.04364 · HTML: https://mlsanity.com/paper/2005.04364/

## Key facts

- Cited by 64 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 May 2020.

## Built on by (most cited first, 30 of 64)

- [Tree of Attacks: Jailbreaking Black-Box LLMs Automatically](https://mlsanity.com/paper/2312.02119/) (2023)
- [Prompting GPT-3 To Be Reliable](https://mlsanity.com/paper/2210.09150/) (2022)
- [Post-hoc Interpretability for Neural NLP: A Survey](https://mlsanity.com/paper/2108.04840/) (2021)
- [Measure and Improve Robustness in NLP Models: A Survey](https://mlsanity.com/paper/2112.08313/) (2021)
- [An Empirical Survey of Data Augmentation for Limited Data Learning in NLP](https://mlsanity.com/paper/2106.07499/) (2021)
- [Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metrics](https://mlsanity.com/paper/2106.14574/) (2021)
- [A Survey of Race, Racism, and Anti-Racism in NLP](https://mlsanity.com/paper/2106.11410/) (2021)
- [NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation](https://mlsanity.com/paper/2112.02721/) (2021)
- [Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasures](https://mlsanity.com/paper/2112.05224/) (2021)
- [Incorporating Hierarchy into Text Encoder: a Contrastive Learning Approach for Hierarchical Text Classification](https://mlsanity.com/paper/2203.03825/) (2022)
- [CLINE: Contrastive Learning with Semantic Negative Examples for Natural Language Understanding](https://mlsanity.com/paper/2107.00440/) (2021)
- [VALUE: Understanding Dialect Disparity in NLU](https://mlsanity.com/paper/2204.03031/) (2022)
- [Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey](https://mlsanity.com/paper/2104.06951/) (2021)
- [Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairs](https://mlsanity.com/paper/2101.10579/) (2021)
- [Order-Disorder: Imitation Adversarial Attacks for Black-box Neural Ranking Models](https://mlsanity.com/paper/2209.06506/) (2022)
- [Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks](https://mlsanity.com/paper/2307.16630/) (2023)
- [Data Governance in the Age of Large-Scale Data-Driven Language Technology](https://mlsanity.com/paper/2206.03216/) (2022)
- [Sociodemographic Bias in Language Models: A Survey and Forward Path](https://mlsanity.com/paper/2306.08158/) (2023)
- [Reliability Testing for Natural Language Processing Systems](https://mlsanity.com/paper/2105.02590/) (2021)
- [Code-Mixing on Sesame Street: Dawn of the Adversarial Polyglots](https://mlsanity.com/paper/2103.09593/) (2021)
- [Achieving Model Robustness through Discrete Adversarial Training](https://mlsanity.com/paper/2104.05062/) (2021)
- [Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial Robustness](https://mlsanity.com/paper/2203.07653/) (2022)
- [Efficient Combinatorial Optimization for Word-level Adversarial Textual Attack](https://mlsanity.com/paper/2109.02229/) (2021)
- [Token-Modification Adversarial Attacks for Natural Language Processing: A Survey](https://mlsanity.com/paper/2103.00676/) (2021)
- [On the Robustness of Intent Classification and Slot Labeling in Goal-oriented Dialog Systems to Real-world Noise](https://mlsanity.com/paper/2104.07149/) (2021)
- [A Differentiable Language Model Adversarial Attack on Text Classifiers](https://mlsanity.com/paper/2107.11275/) (2021)
- [Robustification of Multilingual Language Models to Real-world Noise in Crosslingual Zero-shot Settings with Robust Contrastive Pretraining](https://mlsanity.com/paper/2210.04782/) (2022)
- [Evaluating the Morphosyntactic Well-formedness of Generated Texts](https://mlsanity.com/paper/2103.16590/) (2021)
- [Can Question Rewriting Help Conversational Question Answering?](https://mlsanity.com/paper/2204.06239/) (2022)
- [Don't Retrain, Just Rewrite: Countering Adversarial Perturbations by Rewriting Text](https://mlsanity.com/paper/2305.16444/) (2023)

## Abstract (arXiv)

Training on only perfect Standard English corpora predisposes pre-trained neural networks to discriminate against minorities from non-standard linguistic backgrounds (e.g., African American Vernacular English, Colloquial Singapore English, etc.). We perturb the inflectional morphology of words to craft plausible and semantically similar adversarial examples that expose these biases in popular NLP models, e.g., BERT and Transformer, and show that adversarially fine-tuning them for a single epoch significantly improves robustness without sacrificing performance on clean data.