A broad empirical study of multi-label contrastive losses, plus a new regularized loss, LREG, that improves Macro-F1 on large-label datasets.
An exploration of encoder-decoder approaches to multi-label classification for legal and biomedical text
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multi-Label Contrastive Learning : A Comprehensive Study
A broad empirical study of multi-label contrastive losses, plus a new regularized loss, LREG, that improves Macro-F1 on large-label datasets.