Affect models predict sadness more often and neutrality less often for atypical speech, but the reported fine-tuning gain is evaluated against the same pseudo-label source used to train it.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Affect Models Have Weak Generalizability to Atypical Speech
Affect models predict sadness more often and neutrality less often for atypical speech, but the reported fine-tuning gain is evaluated against the same pseudo-label source used to train it.