Papers by SangHun Im
Hierarchy-aware Biased Bound Margin Loss Function for Hierarchical Text Classification (2024.findings-acl)
Copied to clipboard
| Challenge: | Hierarchical text classification (HTC) is a challenging problem with two key issues: utilizing structural information and mitigating label imbalance. |
| Approach: | They propose a hierarchy-aware biased bound margin loss function for unit-based HTC models that integrates learnable bounds, biases, and a margin to address static thresholding and mitigate label imbalance adaptively. |
| Outcome: | Experimental results show that the proposed model outperforms the global approach and is more robust to label imbalances. |