Enhance Open Tapioca for biological concepts
Opened this issue · 0 comments
lubianat commented
What is your idea?
Open Tapioca is a nice matcher to Wikidata, but it only works for the names of people, organizations and places. It would be cool if we could use it for biological concepts!
What can we do at the Sprint?
Dig into the code of Open Tapíoca and figure out a way of making the Natural Language Processing (NLP) algorithm detect genes (or disease, or proteins).
This would be a cool "deliverable", because it is both relevant for this project and integrated to an external tool (immediate impact!)
What skills does it require?
- Some experience with NLP
- Some experience with python programming