On the Evaluation of Neural Selective Prediction Methods for Natural Language Processing

Zhengyao Gu, Mark Hopkins


Abstract
We provide a survey and empirical comparison of the state-of-the-art in neural selective classification for NLP tasks. We also provide a methodological blueprint, including a novel metric called refinement that provides a calibrated evaluation of confidence functions for selective prediction. Finally, we supply documented, open-source code to support the future development of selective prediction techniques.
Anthology ID:
2023.acl-long.437
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7888–7899
Language:
URL:
https://aclanthology.org/2023.acl-long.437
DOI:
10.18653/v1/2023.acl-long.437
Bibkey:
Cite (ACL):
Zhengyao Gu and Mark Hopkins. 2023. On the Evaluation of Neural Selective Prediction Methods for Natural Language Processing. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7888–7899, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
On the Evaluation of Neural Selective Prediction Methods for Natural Language Processing (Gu & Hopkins, ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2023.acl-long.437.pdf
Video:
 https://preview.aclanthology.org/naacl24-info/2023.acl-long.437.mp4