Self-critical policy-gradient training of a multi-product BERT MLM produces ad headlines that beat LSTM+RL baselines and human submissions on overlap metrics and blind quality/grammar audits.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Ad Headline Generation using Self-Critical Masked Language Model
Self-critical policy-gradient training of a multi-product BERT MLM produces ad headlines that beat LSTM+RL baselines and human submissions on overlap metrics and blind quality/grammar audits.