GAML-BERT: Improving BERT Early Exiting by Gradient Aligned Mutual Learning

Wei Zhu, Xiaoling Wang, Yuan Ni, Guotong Xie. GAML-BERT: Improving BERT Early Exiting by Gradient Aligned Mutual Learning. In Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih, editors, Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 7-11 November, 2021. pages 3033-3044, Association for Computational Linguistics, 2021. [doi]

@inproceedings{ZhuWNX21-0,
  title = {GAML-BERT: Improving BERT Early Exiting by Gradient Aligned Mutual Learning},
  author = {Wei Zhu and Xiaoling Wang and Yuan Ni and Guotong Xie},
  year = {2021},
  url = {https://aclanthology.org/2021.emnlp-main.242},
  researchr = {https://researchr.org/publication/ZhuWNX21-0},
  cites = {0},
  citedby = {0},
  pages = {3033-3044},
  booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 7-11 November, 2021},
  editor = {Marie-Francine Moens and Xuanjing Huang and Lucia Specia and Scott Wen-tau Yih},
  publisher = {Association for Computational Linguistics},
}