Browsing University of Waterloo by Subject "knowledge distillation"
Now showing items 1-1 of 1
-
Towards Effective Utilization of Pretrained Language Models — Knowledge Distillation from BERT
(University of Waterloo, 2020-09-02)In the natural language processing (NLP) literature, neural networks are becoming increasingly deeper and more complex. Recent advancements in neural NLP are large pretrained language models (e.g. BERT), which lead to ...