Thomas Vakili

According to our database, Thomas Vakili authored at least 4 papers between 2021 and 2023.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2023

Using Membership Inference Attacks to Evaluate Privacy-Preserving Language Modeling Fails for Pseudonymizing Data.

Thomas Vakili, Hercules Dalianis

Proceedings of the 24th Nordic Conference on Computational Linguistics, 2023

2022

Downstream Task Performance of BERT Models Pre-Trained Using Automatically De-Identified Clinical Data.

Thomas Vakili, Anastasios Lamproudis, Aron Henriksson, Hercules Dalianis

Proceedings of the Thirteenth Language Resources and Evaluation Conference, 2022

Utility Preservation of Clinical Text After De-Identification.

Thomas Vakili, Hercules Dalianis

Proceedings of the 21st Workshop on Biomedical Language Processing, 2022

2021

Are Clinical BERT Models Privacy Preserving? The Difficulty of Extracting Patient-Condition Associations.

Thomas Vakili, Hercules Dalianis

Proceedings of the AAAI 2021 Fall Symposium on Human Partnership with Medical AI: Design, 2021