-
Underspecification Presents Challenges for Credibility in Modern Machine Learning
ML models often exhibit unexpectedly poor behavior when they are deploye...
11/06/2020 ∙ by Alexander D'Amour, et al. ∙
30
∙
share
read it
-
Measuring and Reducing Gendered Correlations in Pre-trained Models
Pre-trained models have revolutionized natural language understanding. H...
10/12/2020 ∙ by Kellie Webster, et al. ∙
1
∙
share
read it
-
Type B Reflexivization as an Unambiguous Testbed for Multilingual Multi-Task Gender Bias
The one-sided focus on English in previous studies of gender bias in NLP...
09/24/2020 ∙ by Ana Valeria Gonzalez, et al. ∙
0
∙
share
read it
-
Scalable Cross Lingual Pivots to Model Pronoun Gender for Translation
Machine translation systems with inadequate document understanding can m...
06/16/2020 ∙ by Kellie Webster, et al. ∙
0
∙
share
read it
-
Social Biases in NLP Models as Barriers for Persons with Disabilities
Building equitable and inclusive NLP technologies demands consideration ...
05/02/2020 ∙ by Ben Hutchinson, et al. ∙
0
∙
share
read it
-
Automatically Identifying Gender Issues in Machine Translation using Perturbations
The successful application of neural methods to machine translation has ...
04/29/2020 ∙ by Hila Gonen, et al. ∙
0
∙
share
read it
-
Mind the GAP: A Balanced Corpus of Gendered Ambiguous Pronouns
Coreference resolution is an important task for natural language underst...
10/11/2018 ∙ by Kellie Webster, et al. ∙
0
∙
share
read it
