Named Entity Recognition in Swedish Health Records with Character-Based Deep Bidirectional LSTMs

Simon Almgren, Sean Pavlov, Olof Mogren


Abstract
We propose an approach for named entity recognition in medical data, using a character-based deep bidirectional recurrent neural network. Such models can learn features and patterns based on the character sequence, and are not limited to a fixed vocabulary. This makes them very well suited for the NER task in the medical domain. Our experimental evaluation shows promising results, with a 60% improvement in F 1 score over the baseline, and our system generalizes well between different datasets.
Anthology ID:
W16-5104
Volume:
Proceedings of the Fifth Workshop on Building and Evaluating Resources for Biomedical Text Mining (BioTxtM2016)
Month:
December
Year:
2016
Address:
Osaka, Japan
Editors:
Sophia Ananiadou, Riza Batista-Navarro, Kevin Bretonnel Cohen, Dina Demner-Fushman, Paul Thompson
Venue:
WS
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
30–39
Language:
URL:
https://aclanthology.org/W16-5104
DOI:
Bibkey:
Cite (ACL):
Simon Almgren, Sean Pavlov, and Olof Mogren. 2016. Named Entity Recognition in Swedish Health Records with Character-Based Deep Bidirectional LSTMs. In Proceedings of the Fifth Workshop on Building and Evaluating Resources for Biomedical Text Mining (BioTxtM2016), pages 30–39, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
Named Entity Recognition in Swedish Health Records with Character-Based Deep Bidirectional LSTMs (Almgren et al., 2016)
Copy Citation:
PDF:
https://aclanthology.org/W16-5104.pdf
Code
 olofmogren/biomedical-ner-data-swedish