Intermediate Layer Distillation with the Reused Teacher Classifier: A Study on the Importance of the Classifier of Attention-based Models

Hang Zhang, Seyyed Hasan Mozafari, James J. Clark, Brett H. Meyer, Warren J. Gross


Anthology ID:
2024.findings-emnlp.422
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7203–7212
Language:
URL:
https://preview.aclanthology.org/add-emnlp-2024-awards/2024.findings-emnlp.422/
DOI:
10.18653/v1/2024.findings-emnlp.422
Bibkey:
Cite (ACL):
Hang Zhang, Seyyed Hasan Mozafari, James J. Clark, Brett H. Meyer, and Warren J. Gross. 2024. Intermediate Layer Distillation with the Reused Teacher Classifier: A Study on the Importance of the Classifier of Attention-based Models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 7203–7212, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Intermediate Layer Distillation with the Reused Teacher Classifier: A Study on the Importance of the Classifier of Attention-based Models (Zhang et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/add-emnlp-2024-awards/2024.findings-emnlp.422.pdf