Revisiting Intermediate Layer Distillation for Compressing Language Models: An Overfitting Perspective

Jongwoo Ko, Seungjoon Park, Minchan Jeong, Sukjin Hong, Euijai Ahn, Du-Seong Chang, Se-Young Yun. Revisiting Intermediate Layer Distillation for Compressing Language Models: An Overfitting Perspective. In Andreas Vlachos 0001, Isabelle Augenstein, editors, Findings of the Association for Computational Linguistics: EACL 2023, Dubrovnik, Croatia, May 2-6, 2023. pages 158-175, Association for Computational Linguistics, 2023. [doi]

@inproceedings{KoPJHACY23,
  title = {Revisiting Intermediate Layer Distillation for Compressing Language Models: An Overfitting Perspective},
  author = {Jongwoo Ko and Seungjoon Park and Minchan Jeong and Sukjin Hong and Euijai Ahn and Du-Seong Chang and Se-Young Yun},
  year = {2023},
  url = {https://aclanthology.org/2023.findings-eacl.12},
  researchr = {https://researchr.org/publication/KoPJHACY23},
  cites = {0},
  citedby = {0},
  pages = {158-175},
  booktitle = {Findings of the Association for Computational Linguistics: EACL 2023, Dubrovnik, Croatia, May 2-6, 2023},
  editor = {Andreas Vlachos 0001 and Isabelle Augenstein},
  publisher = {Association for Computational Linguistics},
  isbn = {978-1-959429-47-0},
}