A decoder that generates child-to-parent symbolic label sequences, with no graph encoder and no label semantics, matches state-of-the-art hierarchical text classification on three benchmarks at roughly half the inference time.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Transformer-based Autoregressive Decoder Architecture for Hierarchical Text Classification
A decoder that generates child-to-parent symbolic label sequences, with no graph encoder and no label semantics, matches state-of-the-art hierarchical text classification on three benchmarks at roughly half the inference time.