A Case for Soft Loss Functions

Authors

  • Alexandra Uma Queen Mary University
  • Tommaso Fornaciari Università Bocconi
  • Dirk Hovy Università Bocconi
  • Silviu Paun Queen Mary University
  • Barbara Plank University of Copenhagen
  • Massimo Poesio Queen Mary University

DOI:

https://doi.org/10.1609/hcomp.v8i1.7478

Abstract

Recently, Peterson et al. provided evidence of the benefits of using probabilistic soft labels generated from crowd annotations for training a computer vision model, showing that using such labels maximizes performance of the models over unseen data. In this paper, we generalize these results by showing that training with soft labels is an effective method for using crowd annotations in several other ai tasks besides the one studied by Peterson et al., and also when their performance is compared with that of state-of-the-art methods for learning from crowdsourced data.

Downloads

Published

2020-10-01

How to Cite

Uma, A., Fornaciari, T., Hovy, D., Paun, S., Plank, B., & Poesio, M. (2020). A Case for Soft Loss Functions. Proceedings of the AAAI Conference on Human Computation and Crowdsourcing, 8(1), 173-177. https://doi.org/10.1609/hcomp.v8i1.7478