NLPStatTest: A Toolkit for Comparing NLP System Performance

Haotian Zhu, Denise Mak, Jesse Gioannini, Fei Xia


Abstract
Statistical significance testing centered on p-values is commonly used to compare NLP system performance, but p-values alone are insufficient because statistical significance differs from practical significance. The latter can be measured by estimating effect size. In this pa-per, we propose a three-stage procedure for comparing NLP system performance and provide a toolkit, NLPStatTest, that automates the process. Users can upload NLP system evaluation scores and the toolkit will analyze these scores, run appropriate significance tests, estimate effect size, and conduct power analysis to estimate Type II error. The toolkit provides a convenient and systematic way to compare NLP system performance that goes beyond statistical significance testing.
Anthology ID:
2020.aacl-demo.7
Volume:
Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: System Demonstrations
Month:
December
Year:
2020
Address:
Suzhou, China
Editors:
Derek Wong, Douwe Kiela
Venue:
AACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
40–46
Language:
URL:
https://aclanthology.org/2020.aacl-demo.7
DOI:
Bibkey:
Cite (ACL):
Haotian Zhu, Denise Mak, Jesse Gioannini, and Fei Xia. 2020. NLPStatTest: A Toolkit for Comparing NLP System Performance. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: System Demonstrations, pages 40–46, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
NLPStatTest: A Toolkit for Comparing NLP System Performance (Zhu et al., AACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.aacl-demo.7.pdf
Code
 nlp-stat-test/nlp-stat-test