FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders

Pretrained text encoders, such as BERT, have been applied increasingly in various natural language processing (NLP) tasks, and have recently demonstrated significant performance gains. However, recent studies have demonstrated the existence of social bias in these pretrained NLP models. Although pri...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2021-03
Main Authors: Cheng, Pengyu, Weituo Hao, Yuan, Siyang, Si, Shijing, Lawrence, Carin
Format: Article
Language:English
Subjects:
Bias
Coders
Human bias
Natural language processing
Retraining
Sentences
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Pretrained text encoders, such as BERT, have been applied increasingly in various natural language processing (NLP) tasks, and have recently demonstrated significant performance gains. However, recent studies have demonstrated the existence of social bias in these pretrained NLP models. Although prior works have made progress on word-level debiasing, improved sentence-level fairness of pretrained encoders still lacks exploration. In this paper, we proposed the first neural debiasing method for a pretrained sentence encoder, which transforms the pretrained encoder outputs into debiased representations via a fair filter (FairFil) network. To learn the FairFil, we introduce a contrastive learning framework that not only minimizes the correlation between filtered embeddings and bias words but also preserves rich semantic information of the original sentences. On real-world datasets, our FairFil effectively reduces the bias degree of pretrained text encoders, while continuously showing desirable performance on downstream tasks. Moreover, our post-hoc method does not require any retraining of the text encoders, further enlarging FairFil's application space.
ISSN:2331-8422