Adversarial bootstrapping, weighting the generator's maximum-likelihood loss by an adversarially trained and similarity-bootstrapped discriminator, improves response quality in multi-turn dialogue models.
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
-
Adversarial Bootstrapping for Dialogue Model Training
Adversarial bootstrapping, weighting the generator's maximum-likelihood loss by an adversarially trained and similarity-bootstrapped discriminator, improves response quality in multi-turn dialogue models.