The recognition and normalization of clinical information, such as tumor morphology mentions, is an important, but complex process consisting of multiple subtasks. In this paper, we describe our system for the CANTEMIST shared task, which is able to extract, normalize and rank ICD codes from Spanish electronic health records using neural sequence labeling and parsing approaches with context-aware embeddings. Our best system achieves 85.3 F1, 76.7 F1, and 77.0 MAP for the three tasks, respectively.
@article{arxiv.2010.12322,
title = {NLNDE at CANTEMIST: Neural Sequence Labeling and Parsing Approaches for Clinical Concept Extraction},
author = {Lukas Lange and Xiang Dai and Heike Adel and Jannik Strötgen},
journal= {arXiv preprint arXiv:2010.12322},
year = {2020}
}