spaCy get confidence on entity classification?

[israelc]

Anybody can help on how to get the confidence of ner classification? Is there a way to do this?

[andy]

There’s not a built-in method, but you can get approximate confidence using the code posted here:

Displaying a confidence score next to a user-defined entity

Hmm. Actually that code looks weird. Try this: text = content doc = nlp.make_doc(text) (beams, somethingelse) = nlp.entity.beam_parse([doc], beam_width=16, beam_density=0.0001) for score, ents in nlp.entity.moves.get_beam_parses(beams[0]): print (score, ents) entity_scores = defaultdict(float) for start, end, label in ents: # print ("here") entity_scores[(start, end, label)] += score print ('entity_scores', entity_scores)

[honnibal]

Thanks Andy! Yes that’s correct, that’s the best current code to get entity scores at the moment.