1 |
Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Challenges in Automated Debiasing for Toxic Language Detection ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Extracting and Inferring Personal Attributes from Dialogue ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Challenges in Automated Debiasing for Toxic Language Detection
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Linguistically-Informed Transformations (LIT): A Method for Automatically Generating Contrast Sets ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|