The Biological Text Mining Unit at BSC and CNIO are currently organizing the first task on chemical & drug mention recognition from Spanish medical texts called PharmaCoNER (Pharmacological Substances, Compounds and proteins and Named Entity Recognition track), as part of the upcoming BioNLP-OST 2019 Workshop (November, 3rd-4th, 2019).
Inspired by the success of the BioCreative CHEMDNER tasks and the i2b2 medication challenge, this task will address the automatic extraction of chemical, drug, gene/protein mentions from clinical case studies written in Spanish.
With over 470 million native speakers, there is an increasing interest to process not only the medical literature written in Spanish but also the other clinical texts, in particular electronic health records. There are estimates that every 10 minutes, tens of thousands of EHRs are written in only in Spanish medical institutions.
The main aim is to promote the development of medical named entity recognition tools of practical relevance, determining the current state-of-the art, identifying challenges and comparing the strategies and results to those published for English data.
Evaluation of automatic predictions for this task will have two different scenarios or tracks:
- Track 1: NER offset and entity classification
- Track 2: Concept indexing
For additional information please have a look at:
- PharmaCoNER: http://temu.bsc.es/pharmaconer
- BioNLP-OST 2019 Workshop: https://2019.bionlp-ost.org/
There will be a prize for both sub-tracks: 1,000€ to each sub-track winner, 500€ to the second teams and 200€ to the third teams.
The results of the track will be presented at the BioNLP workshop and a journal special issue will be published after the event in coordination with other track organizers.