Are Larger Pretrained Language Models Uniformly Better? Comparing Performance at the Instance Level

Ruiqi Zhong, Dhruba Ghosh, Dan Klein, Jacob Steinhardt


Anthology ID:
2021.findings-acl.334
Volume:
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3813–3827
Language:
URL:
https://aclanthology.org/2021.findings-acl.334
DOI:
10.18653/v1/2021.findings-acl.334
Bibkey:
Cite (ACL):
Ruiqi Zhong, Dhruba Ghosh, Dan Klein, and Jacob Steinhardt. 2021. Are Larger Pretrained Language Models Uniformly Better? Comparing Performance at the Instance Level. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 3813–3827, Online. Association for Computational Linguistics.
Cite (Informal):
Are Larger Pretrained Language Models Uniformly Better? Comparing Performance at the Instance Level (Zhong et al., Findings 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-acl.334.pdf
Video:
 https://aclanthology.org/2021.findings-acl.334.mp4
Code
 ruiqi-zhong/acl2021-instance-level
Data
GLUESSTSST-2