Why Skip If You Can Combine: A Simple Knowledge Distillation Technique for Intermediate Layers

Yimeng Wu, Peyman Passban, Mehdi Rezagholizadeh, Qun Liu. Why Skip If You Can Combine: A Simple Knowledge Distillation Technique for Intermediate Layers. In Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu, editors, Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online, November 16-20, 2020. pages 1016-1021, Association for Computational Linguistics, 2020. [doi]

@inproceedings{WuPRL20-0,
  title = {Why Skip If You Can Combine: A Simple Knowledge Distillation Technique for Intermediate Layers},
  author = {Yimeng Wu and Peyman Passban and Mehdi Rezagholizadeh and Qun Liu},
  year = {2020},
  url = {https://www.aclweb.org/anthology/2020.emnlp-main.74/},
  researchr = {https://researchr.org/publication/WuPRL20-0},
  cites = {0},
  citedby = {0},
  pages = {1016-1021},
  booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online, November 16-20, 2020},
  editor = {Bonnie Webber and Trevor Cohn and Yulan He and Yang Liu},
  publisher = {Association for Computational Linguistics},
  isbn = {978-1-952148-60-6},
}