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.
Using convolutional neural network with bert for intent determination
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.