Uncertainty-Aware Natural Language Inference with Stochastic Weight Averaging

Aarne Talman, Hande Celikkanat, Sami Virpioja, Markus Heinonen, Jörg Tiedemann


Abstract
This paper introduces Bayesian uncertainty modeling using Stochastic Weight Averaging-Gaussian (SWAG) in Natural Language Understanding (NLU) tasks. We apply the approach to standard tasks in natural language inference (NLI) and demonstrate the effectiveness of the method in terms of prediction accuracy and correlation with human annotation disagreements. We argue that the uncertainty representations in SWAG better reflect subjective interpretation and the natural variation that is also present in human language understanding. The results reveal the importance of uncertainty modeling, an often neglected aspect of neural language modeling, in NLU tasks.
Anthology ID:
2023.nodalida-1.37
Volume:
Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)
Month:
May
Year:
2023
Address:
Tórshavn, Faroe Islands
Editors:
Tanel Alumäe, Mark Fishel
Venue:
NoDaLiDa
SIG:
Publisher:
University of Tartu Library
Note:
Pages:
358–365
Language:
URL:
https://aclanthology.org/2023.nodalida-1.37
DOI:
Bibkey:
Cite (ACL):
Aarne Talman, Hande Celikkanat, Sami Virpioja, Markus Heinonen, and Jörg Tiedemann. 2023. Uncertainty-Aware Natural Language Inference with Stochastic Weight Averaging. In Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa), pages 358–365, Tórshavn, Faroe Islands. University of Tartu Library.
Cite (Informal):
Uncertainty-Aware Natural Language Inference with Stochastic Weight Averaging (Talman et al., NoDaLiDa 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.nodalida-1.37.pdf