A Contrastive Self-distillation BERT with Kernel Alignment-Based Inference
- 26 June 2023
- book chapter
- Published by Springer Nature
- p. 553-565
Abstract
No abstract availableKeywords
This publication has 20 references indexed in Scilit:
- Accelerating Pretrained Language Model Inference Using Weighted Ensemble Self-distillation2021
- LeeBERT: Learned Early Exit for BERT with cross-level optimization2021
- BERT-of-Theseus: Compressing BERT by Progressive Module Replacing2020
- Transformers: State-of-the-Art Natural Language Processing2020
- The Right Tool for the Job: Matching Model and Instance Complexities2020
- DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference2020
- FastBERT: a Self-distilling BERT with Adaptive Inference Time2020
- Patient Knowledge Distillation for BERT Model Compression2019
- GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding2018
- BranchyNet: Fast inference via early exiting from deep neural networks2016