← Search

Gibaeg Kim

2 accepted papers

2024

Hierarchy-aware Biased Bound Margin Loss Function for Hierarchical Text Classification

ACL 2024findings

Hierarchical text classification (HTC) is a challenging problem with two key issues: utilizing structural information and mitigating label imbalance. Recently, the unit-based approach generating unit-based feature representations has outperformed the global approach focusing on a global feature repr…

2023

Hierarchical Text Classification as Sub-hierarchy Sequence Generation

AAAI 2023technical

Hierarchical text classification (HTC) is essential for various real applications. However, HTC models are challenging to develop because they often require processing a large volume of documents and labels with hierarchical taxonomy. Recent HTC models based on deep learning have attempted to incorp…