TERN is a rule-based and hybrid (rule-union-CRF) temporal expressions identification and normalisation software; designed for clinical data. The identification (TEid) and normalization component (Clinical NorMA) were used and evaluated as part of the Temporal Relation challenge (i2b2 2012). This software provides various features for easy integration into existing pipelines (e.g., server mode); see browse code / README file.
Nota bene: binaries are compiled with OpenJDK.
Kovačević A, Dehghan A, Filannino M, Keane JA, Nenadic, G: Combining rules and machine-learning for extraction of temporal expressions and events from clinical narratives. Journal of the American Medical Informatics Association. JAMIA 20(5): 859-866 (2013)
- JAVA-based (primarily)
- (Socket) Server mode
- Input/Output stream
- GATE output
- Offset file output
Follow Clinical TERN
Rate This ProjectLogin To Rate This Project
Thank you for your work.