TernaryBERT

2000년 도입 · 논문 2편에서 사용

TernaryBERT is a Transformer-based model which ternarizes the weights of a pretrained BERT model to $\{-1,0,+1\}$, with different granularities for word embedding and weights in the Transformer layer. Instead of directly using knowledge distillation to compress a model, it is used to improve the performance of ternarized student model with the same size as the teacher model. In this way, we transfer the knowledge from the highly-accurate teacher model to the ternarized student model with smaller capacity.

출처: TernaryBERT: Distillation-aware Ultra-low Bit BERT

소개 논문: TernaryBERT: Distillation-aware Ultra-low Bit BERT