A fully hyperbolic attention model using Busemann energy in Poincaré discs produces emotion predictions from text that generalize well even at low embedding dimensions.
Not all negatives are equal: Label-aware contrastive loss for fine-grained text classification
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
ImpSH improves cross-domain generalization in implicit hate speech classification by aligning posts with implied statements and applying context-bounded semi-hard negative mining within a triplet learning setup.
citing papers explorer
-
Busemann energy-based attention for emotion analysis in Poincar\'e discs
A fully hyperbolic attention model using Busemann energy in Poincaré discs produces emotion predictions from text that generalize well even at low embedding dimensions.
-
Aligning Implied Statements for Implicit Hate Speech Generalizability with Context-Bounded Semi-hard Negative Mining
ImpSH improves cross-domain generalization in implicit hate speech classification by aligning posts with implied statements and applying context-bounded semi-hard negative mining within a triplet learning setup.