no code implementations • EMNLP (Louhi) 2020 • Hanna Berg, Aron Henriksson, Hercules Dalianis
The impact of de-identification on data quality and, in particular, utility for developing models for downstream tasks has been more thoroughly studied for structured data than for unstructured text.
no code implementations • NoDaLiDa 2021 • Hanna Berg, Hercules Dalianis
This paper describes a freely available web-based demonstrator called HB Deid.
no code implementations • LREC 2020 • Hanna Berg, Hercules Dalianis
An abundance of electronic health records (EHR) is produced every day within healthcare.
no code implementations • WS 2019 • Hanna Berg, Taridzo Chomutare, Hercules Dalianis
This article presents experiments with pseudonymised Swedish clinical text used as training data to de-identify real clinical text with the future aim to transfer non-sensitive training data to other hospitals.