@inproceedings{wu-etal-2021-one,
title = "One Teacher is Enough? Pre-trained Language Model Distillation from Multiple Teachers",
author = "Wu, Chuhan and
Wu, Fangzhao and
Huang, Yongfeng",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://preview.aclanthology.org/fix-sig-urls/2021.findings-acl.387/",
doi = "10.18653/v1/2021.findings-acl.387",
pages = "4408--4413"
}
Markdown (Informal)
[One Teacher is Enough? Pre-trained Language Model Distillation from Multiple Teachers](https://preview.aclanthology.org/fix-sig-urls/2021.findings-acl.387/) (Wu et al., Findings 2021)
ACL