This task focuses on the recognition of named entities NER and the classification of these entities according to their types. In particular, it is focused on the identification and classification of sensitive information (e.g., patient names, telephones, addresses, etc.) in medical documents.
The MEDDOCAN annotation guidelines defined a total of 29 entity types, that area available at: http://ceur-ws.org/Vol-2421/MEDDOCAN_overview.pdf
Publication
Montserrat Marimon, Aitor Gonzalez-Agirre, Ander Intxaurrondo, Heidy Rodríguez, Jose Lopez Martin, Marta Villegas, Martin Krallinger (2019) “Automatic De-identification of Medical Texts in Spanish: the MEDDOCAN Track, Corpus, Guidelines, Methods and Evaluation of Results.” In: IberLEF@ SEPLN. 2019, pp. 618–638.
Competition
Language
Spanish
NLP topic
Abstract task
Dataset
Year
2019
Publication link
Ranking metric
F1
Task results
| System | MicroPrecision | MicroRecall | MicroF1 Sort ascending |
|---|---|---|---|
| lukas.lange-1 | 0.9698 | 0.9694 | 0.9696 |
| lukas.lange-2 | 0.9708 | 0.9684 | 0.9696 |
| lukas.lange-3 | 0.9704 | 0.9686 | 0.9695 |
| lukas.lange-4 | 0.9696 | 0.9677 | 0.9686 |
| lukas.lange-5 | 0.9672 | 0.9638 | 0.9655 |
