Exploiting natural language processing in the clinical domain requires de-identification, i.e., anonymization of personal information in texts. However, current research considers de-identification and downstream tasks, such as concept extraction, only in isolation and does not study the effects of de-identification on other tasks. In this paper, we close this gap by reporting concept extraction performance on automatically anonymized data and investigating joint models for de-identification and concept extraction. In particular, we propose a stacked model with restricted access to privacy-sensitive information and a multitask model. We set the new state of the art on benchmark datasets in English (96.1% F1 for de-identification and 88.9% F1 for concept extraction) and Spanish (91.4% F1 for concept extraction).
@article{arxiv.2005.09397,
title = {Closing the Gap: Joint De-Identification and Concept Extraction in the Clinical Domain},
author = {Lukas Lange and Heike Adel and Jannik Strötgen},
journal= {arXiv preprint arXiv:2005.09397},
year = {2020}
}