Hurtful words - quantifying biases in clinical contextual word embeddings

Haoran Zhang
Haoran Zhang
Amy X. Lu
Amy X. Lu
Mohamed Abdalla
Mohamed Abdalla
Matthew B. A. McDermott
Matthew B. A. McDermott

ACM CHIL '20: ACM Conference on Health, Inference, and Learning Toronto Ontario Canada April, 2020, pp. 110-120, 2020.

Cited by: 1|Views4
EI

Abstract:

In this work, we examine the extent to which embeddings may encode marginalized populations differently, and how this may lead to a perpetuation of biases and worsened performance on clinical tasks. We pretrain deep embedding models (BERT) on medical notes from the MIMIC-III hospital dataset, and quantify potential disparities using two a...More

Code:

Data:

Your rating :
0

 

Tags
Comments