Detecting seven types of named entities and hedge cues in a corpus of pediatric ultrasound reports from an Argentinian public hospital
The following entities are distinguished: Anatomical Entity, Finding, Location, Measure, Type of Measure, Degree, and Abbreviation.
The following hedge cues are considered: Negation, Uncertainty, and Conditional-Temporal.
Publication
Viviana Cotik, Laura Alonso Alemany, Darío Filippo, Franco Luque, Roland Roller, Jorge Vivaldi, Ammer Ayach, Fernando Carranza, Lucas Defrancesca, Antonella Dellanzo, Macarena Fernández Urquiza (2021) Overview of CLEF eHealth Task 1 - SpRadIE: A challenge on information extraction from Spanish Radiology Reports. Proceedings of Overview of CLEF eHealth Task 1 - SpRadIE: A challenge on information extraction from Spanish Radiology Reports.
Language
Spanish (Argentina)
NLP topic
Abstract task
Dataset
Year
2021
Publication link
Ranking metric
Micro F
Task results
| System | MicroPrecision | MicroRecall | MicroF1 Sort ascending |
|---|---|---|---|
| EdIE (UK) run2 | 0.8724 | 0.8385 | 0.8551 |
| LSI (Spain) run1 | 0.9028 | 0.7833 | 0.8388 |
| CTB (Spain, Colombia) run3 | 0.7862 | 0.7832 | 0.7847 |
| HULAT (Spain) run1 | 0.7838 | 0.7308 | 0.7564 |
| SINAI (Spain) run2 | 0.8607 | 0.6443 | 0.7370 |
