Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Bayesian Spectral Emotion Transition Discovery from Multi-Annotator Disagreement
Keito Inoshita, Takato Ueno
Emotions evolve through the dynamics of conversation, and understanding their transition structure is foundational to applications ranging from mental-health screening to dialogue…
cs.AI2026
Uncertainty Decomposition via Cyclical SG-MCMC and Soft-label Learning for Subjective NLP
Keito Inoshita, Takato Ueno
Annotator disagreement in emotion classification reflects ambiguity intrinsic to emotion concepts and is essential for predictor-quality assessment in subjective NLP. Yet no prior…