Please, Don’t Forget the Difference and the Confidence Interval when Seeking for the State-of-the-Art Status

Yves Bestgen


Abstract
This paper argues for the widest possible use of bootstrap confidence intervals for comparing NLP system performances instead of the state-of-the-art status (SOTA) and statistical significance testing. Their main benefits are to draw attention to the difference in performance between two systems and to help assessing the degree of superiority of one system over another. Two cases studies, one comparing several systems and the other based on a K-fold cross-validation procedure, illustrate these benefits.
Anthology ID:
2022.lrec-1.640
Volume:
Proceedings of the Thirteenth Language Resources and Evaluation Conference
Month:
June
Year:
2022
Address:
Marseille, France
Editors:
Nicoletta Calzolari, Frédéric Béchet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Hélène Mazo, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
5956–5962
Language:
URL:
https://aclanthology.org/2022.lrec-1.640
DOI:
Bibkey:
Cite (ACL):
Yves Bestgen. 2022. Please, Don’t Forget the Difference and the Confidence Interval when Seeking for the State-of-the-Art Status. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 5956–5962, Marseille, France. European Language Resources Association.
Cite (Informal):
Please, Don’t Forget the Difference and the Confidence Interval when Seeking for the State-of-the-Art Status (Bestgen, LREC 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.lrec-1.640.pdf
Code
 ybestgen/bootcirealdata