Uncertainty-Aware Natural Language Inference with Stochastic Weight AveragingDownload PDF

Published: 20 Mar 2023, Last Modified: 21 Apr 2024NoDaLiDa 2023Readers: Everyone
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.
Student Paper: Yes, the first author is a student
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 2 code implementations](https://www.catalyzex.com/paper/arxiv:2304.04726/code)
3 Replies

Loading