Adding a human-attention similarity term to a transformer loss improved accuracy on small, imbalanced datasets in two NLP tasks, but the printed loss equation has the wrong sign for the stated goal.
Coca: Cost-effective collaborative annotation system by combining experts and amateurs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Aligning Human and Machine Attention for Enhanced Supervised Learning
Adding a human-attention similarity term to a transformer loss improved accuracy on small, imbalanced datasets in two NLP tasks, but the printed loss equation has the wrong sign for the stated goal.