Work

It’s Morphin’ Time! Combating Linguistic Discrimination with Inflectional Perturbations

Year: 2020

Type: conference-paper

Abstract: Training on only perfect Standard English corpora predisposes pre-trained neural networks to discriminate against minorities from nonstandard 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. 1

Source: Annual Meeting of the Association for Computational Linguistics (ACL)

DOI: 10.18653/v1/2020.acl-main.263

Authors: Samson Tan, Shafiq Joty, Min-Yen Kan, Richard Socher

Institutions: National University of Singapore, Nanyang Technological University, Salesforce (United States)

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDG: Reduced inequalities

Open Access status: hybrid

OpenAlex ID: W3023553115