A toxicity model trained without identity-targeting comments has similar overall AUC but worse per-subgroup accuracy than a model trained on mixed data, especially on false negatives.
Jigsaw Unintended Bias in Toxicity Classifica- tion
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Debiasing Personal Identities in Toxicity Classification
A toxicity model trained without identity-targeting comments has similar overall AUC but worse per-subgroup accuracy than a model trained on mixed data, especially on false negatives.