Abstract
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.- Anthology ID:
- 2020.acl-main.263
- Volume:
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2920–2935
- Language:
- URL:
- https://aclanthology.org/2020.acl-main.263
- DOI:
- 10.18653/v1/2020.acl-main.263
- Cite (ACL):
- Samson Tan, Shafiq Joty, Min-Yen Kan, and Richard Socher. 2020. It’s Morphin’ Time! Combating Linguistic Discrimination with Inflectional Perturbations. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 2920–2935, Online. Association for Computational Linguistics.
- Cite (Informal):
- It’s Morphin’ Time! Combating Linguistic Discrimination with Inflectional Perturbations (Tan et al., ACL 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-1/2020.acl-main.263.pdf
- Code
- salesforce/morpheus
- Data
- SQuAD