@article{furtherboostingbertbasedmodelsby,
  title = {BERT's output layer recognizes all hidden layers? Some Intriguing Phenomena and a simple way to boost BERT},
  author = {Wei-Tsung Kao and Tsung-Han Wu and Po-Han Chi and Chun-Cheng Hsieh and Hung-Yi Lee},
  year = {2020},
  eprint = {2001.09309},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2001.09309v2},
}