Revisiting Softmax for Uncertainty Approximation in Text Classification

Andreas Nugaard Holm, Dustin Wright*, Isabelle Augenstein

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

4 Citations (Scopus)
16 Downloads (Pure)

Abstract

Uncertainty approximation in text classification is an important area with applications in domain adaptation and interpretability. One of the most widely used uncertainty approximation methods is Monte Carlo (MC) dropout, which is computationally expensive as it requires multiple forward passes through the model. A cheaper alternative is to simply use a softmax based on a single forward pass without dropout to estimate model uncertainty. However, prior work has indicated that these predictions tend to be overconfident. In this paper, we perform a thorough empirical analysis of these methods on five datasets with two base neural architectures in order to identify the trade-offs between the two. We compare both softmax and an efficient version of MC dropout on their uncertainty approximations and downstream text classification performance, while weighing their runtime (cost) against performance (benefit). We find that, while MC dropout produces the best uncertainty approximations, using a simple softmax leads to competitive, and in some cases better, uncertainty estimation for text classification at a much lower computational cost, suggesting that softmax can in fact be a sufficient uncertainty estimate when computational resources are a concern.

Original languageEnglish
Article number420
JournalInformation (Switzerland)
Volume14
Issue number7
Number of pages16
ISSN2078-2489
DOIs
Publication statusPublished - 2023

Bibliographical note

Publisher Copyright:
© 2023 by the authors.

Keywords

  • efficiency
  • text classification
  • uncertainty quantification

Cite this