Iterative human adversarial attacks and retraining make offensive-language detectors in dialogue harder to fool, and dialogue context is critical for detecting those attacks.
Title resolution pending
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
-
Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack
Iterative human adversarial attacks and retraining make offensive-language detectors in dialogue harder to fool, and dialogue context is critical for detecting those attacks.