Participant systems have to automatically assign ICD10 codes (CIE-10, in Spanish) to clinical case documents, being evaluated against manually generated ICD10 codifications.
In addition to the Spanish data we will also include training, development and test set documents automatically translated into English.
Following the success of previous eHealth CLEF efforts or medical text mining tasks like MEDDOCAN or PharmaCoNER, we foresee that this task will be influential not only in terms of determining the most competitive approaches which might range from sophisticated term look-up to multi-class document classification systems using machine learning approaches.
Participation and useful info
1. CodiEsp web, info & detailed description: http://temu.bsc.es/codiesp/
2. Registration for CodiEsp (Multilingual Information Extraction eHealth track): http://temu.bsc.es/codiesp/index.php/2019/09/19/registration/
3. Training and development set: https://zenodo.org/record/3633048#.XjRNut-YU5k
4. Additional training resources: https://zenodo.org/record/3606626#.XhyWLN-YU5k
Main CodiEsp Track organizers
• Martin Krallinger, Barcelona Supercomputing Center.
• Antonio Miranda, Barcelona Supercomputing Center.
• Aitor Gonzalez-Agirre, Barcelona Supercomputing Center.
• Marta Villegs, Barcelona Supercomputing Center.
• Jordi Armengol, Barcelona Supercomputing Center.
Important Dates
Jan 13 Train, development and additional training resources set release (Spanish)
February 12 Train, development set release (English machine translation)
April 28 Task setting discussion workshop at MIE2020 (Geneva)
May 3 End of evaluation
May 5 Results notified
May 24 Paper submission
Jun 28 Camera-ready paper submission
Sep 22-25 CLEF 2020 Conference (Thessaloniki, Greece)
|