Uncertainty-Aware Natural Language Inference with Stochastic Weight Averaging

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

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.
Original languageEnglish
Title of host publicationProceedings of the 24th Nordic Conference on Computational Linguistics
EditorsTanel Alumäe , Mark Fishel
Number of pages8
Place of PublicationTartu
PublisherUniversity of Tartu Library
Publication date2023
Pages358-365
ISBN (Electronic)978-99-1621-999-7
Publication statusPublished - 2023
MoE publication typeA4 Article in conference proceedings
EventNordic Conference on Computational Linguistics - Tórshavn, Faroe Islands
Duration: 22 May 202324 May 2023
Conference number: 24

Publication series

NameNEALT Proceedings Series
PublisherUniversity of Tartu Library
Number52
ISSN (Print)1736-8197
ISSN (Electronic)1736-6305

Fields of Science

  • 6121 Languages
  • 113 Computer and information sciences

Cite this