Multi-Layer feature fusion with Layer-GAT and adaptive readout for transformer text classification

Abstract In recent years, Transformer-based pre-trained language models have significantly advanced text classification. However, the complementary semantic information embedded in their multilayer hidden representations remains underutilized, often leading to inconsistent performance across differe...

Descripció completa

Dades bibliogràfiques

Autors principals:	Xinrong Zhan, Xintao Zhan, Junwen Lu, Shaobo Kang
Format:	Artigo
Idioma:	Inglês
Publicat:	Springer 2026-04-01
Col·lecció:	Journal of King Saud University: Computer and Information Sciences
Matèries:	Text classification Transformer Multi-layer feature fusion Graph attention network Adaptive readout
Accés en línia:	https://doi.org/10.1007/s44443-026-00739-x
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!