Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/172420
Title: It’s Morphin’ Time! Combating Linguistic Discrimination with Inflectional Perturbations
Authors: Samson Tan
Shafiq Joty
Min-Yen Kan 
Richard Socher
Issue Date: 2020
Citation: Samson Tan, Shafiq Joty, Min-Yen Kan, Richard Socher (2020). It’s Morphin’ Time! Combating Linguistic Discrimination with Inflectional Perturbations. Proceedings of the 2020 Annual Meeting of the Association of Computational Linguistics (ACL '20) : 1-16. ScholarBank@NUS Repository.
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.
Source Title: Proceedings of the 2020 Annual Meeting of the Association of Computational Linguistics (ACL '20)
URI: https://scholarbank.nus.edu.sg/handle/10635/172420
Appears in Collections:Elements
Staff Publications

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
2005.04364v1.pdf718.89 kBAdobe PDF

OPEN

Pre-printView/Download

Page view(s)

11
checked on Sep 17, 2020

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.