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

• Główni autorzy: Abdalla, Mohamed (Autor), Abdalla, Moustafa (Autor), Hirst, Graeme (Autor), Rudzicz, Frank (Autor)
• Format: Książka
• Wydane: JMIR Publications, 2020-07-01T00:00:00Z.
• Hasła przedmiotowe: article
• Dostęp online: Connect to this object online.

BackgroundWord 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. ObjectiveThis paper aims to d...