2025.emnlp-main.472@ACL

Total: 1

#1 HYDRA: A Multi-Head Encoder-only Architecture for Hierarchical Text Classification [PDF] [Copy] [Kimi] [REL]

Authors: Fabian Karl, Ansgar Scherp

We introduce HYDRA, a simple yet effective multi-head encoder-only architecture for hierarchical text classification that treats each level in the hierarchy as a separate classification task with its own label space. State-of-the-art approaches rely on complex components like graph encoders, label semantics, and autoregressive decoders. We demonstrate that such complexity is often unnecessary. Through parameter sharing and level-specific parameterization, HYDRA enables flat models to incorporate hierarchical awareness without architectural complexity. Experiments on four benchmarks (NYT, RCV1-V2, BGC, and WOS) demonstrate that HYDRA always increases the performance over flat models and matches or exceeds the performance of complex state-of-the-art methods.

Subject: EMNLP.2025 - Main