Thomas Vakili is a PhD student at the Department of Computer and Systems Sciences at Stockholm University. The focus of his research is Natural Language Processing. He is part of the DataLEASH project and his supervisor is Professor Hercules Dalianis.
He has a M.Sc. in computer science and engineering (civ.ing. i datateknik) from KTH Royal Institute of Technology. He also has industry experience from working as a IT consultant, primarily as a back-end developer and data engineer.
Vakili, T. and Dalianis, H., 2021. Are Clinical BERT Models Privacy Preserving? The Difficulty of Extracting Patient-Condition Associations. Presented at the Association for the Advancement of Artificial Intelligence Fall 2021 Symposium in HUman partnership with Medical Artificial iNtelligence (HUMAN.AI).
Vakili, T., 2020. A Method for the Assisted Translation of QA Datasets Using Multilingual Sentence Embeddings. An extended abstract of my master's thesis presented at the workshop on RESOURCEs and representations For Under-resourced Languages and domains.
Vakili, T., 2020. A Method for the Assisted Translation of QA Datasets Using Multilingual Sentence Embeddings.
Vakili, T., 2016. A Comparison of Clustering the Swedish Political Twittersphere Based on Social Interactions and on Tweet Content.
I am currently working on to what extent masked language models (such as BERT) leak sensitive information about their training data. Since BERT-style models are very common, especially for lesser-resourced languages, this could have significant privacy implications.
Don't hesitate to contact me if you are interested in collaborating!