Description
import re
re_tokenise = re.compile(r"((?:\w|'|ÔÇÖ)+)")
from medical_named_entity_recognition import find_diseases
tokens = re_tokenise.findall("diabetes")
find_diseases(tokens)
Expected Behaviour
I would expect it to recognise "diabetes" alone - we need to work out how to expand the dict to do this without too many false positives
Description
Expected Behaviour
I would expect it to recognise "diabetes" alone - we need to work out how to expand the dict to do this without too many false positives