LAD: Layer-Wise Adaptive Distillation for BERT Model Compression.

Lin, Ying-Jia; Chen, Kuan-Yu; Kao, Hung-Yu

Lin, Ying-Jia; Chen, Kuan-Yu; Kao, Hung-Yu.

Afiliación

Lin YJ; Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan 70101, Taiwan.
Chen KY; Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan 70101, Taiwan.
Kao HY; Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan 70101, Taiwan.

Sensors (Basel) ; 23(3)2023 Jan 28.

Article en En | MEDLINE | ID: mdl-36772523

Palabras clave

BERT; deep learning; knowledge distillation; model compression; natural language processing; text classification

Texto completo

Imprimir

XML

PubMed Links

Buscar en Google

Texto completo: 1 Colección: 01-internacional Banco de datos: MEDLINE Idioma: En Revista: Sensors (Basel) Año: 2023 Tipo del documento: Article País de afiliación: Taiwán

Texto completo

Imprimir

XML

PubMed Links

Buscar en Google