Exploring the Privacy-Preserving Properties of Word Embeddings: Algorithmic Validation Study.

Journal: Journal of medical Internet research
Published Date: Jul 15, 2020

Abstract

BACKGROUND: Word embeddings are dense numeric vectors used to represent language in neural networks. Until recently, there had been no publicly released embeddings trained on clinical data. Our work is the first to study the privacy implications of releasing these models.

Authors

  • Mohamed Abdalla
    ICES, Toronto, Canada.
  • Moustafa Abdalla
    Computational Statistics & Machine Learning Group, Department of Statistics, University of Oxford, Oxford, UK.
  • Graeme Hirst
    Department of Computer Science, University of Toronto, Toronto, Canada.
  • Frank Rudzicz
    University of Toronto, Toronto, Canada.

Keywords

External Resources

Popular Topics
Recent Journals