umcu / clinlp

A Python library for performing NLP on clinical text written in Dutch
GNU General Public License v3.0
33 stars 0 forks source link

Add paragraph detection #71

Open vmenger opened 2 months ago

vmenger commented 2 months ago

Clinical texts often container paragraphs, it would be nice to have a structured way to detect these (along with their heading). This information can also be picked up by subsequent components, e.g. an entity in a paragraph 'Family History' should be labeled with an appropriate qualifier.

Some inspiration: https://github.com/medspacy/medspacy/tree/master/medspacy/section_detection Maybe even incorporate this directly?