conftrace_

teacher assistant

3 papers

Explore in graph

Also known as

TA

Co-occurring keywords · papers mentioning both

knowledge distillation (3) model compression (2) extreme compression (1) closed-source model (1) neural network (1) teacher student (1) teacher-student learning (1) multilingual neural machine translation (1) student network (1) soft label (1)

Papers

Minimal Distillation Schedule for Extreme Language Model Compression EACL 2024 TAeKD: Teacher Assistant Enhanced Knowledge Distillation for Closed-Source Multilingual Neural Machine Translation COLING 2024 Improved Knowledge Distillation via Teacher Assistant AAAI 2020