nlp - how find entities for each row of a big data?

Question

I havs a million of rows. in each row there is a job title with some explanation. I want to remove entities from each job title with entities recognition. I am wondering how I can do that with NLTK? it is very easy in spacy . It is just like the following:

ents=[str(ent) for ent in data.ents if not ent.label_ in [str('ORG'), str('PERSON')]]

I just removed 2 label of entities. I can't use spacy now because it has limit on letters. could you tell me how I can do the same in NLTK?

question from:https://stackoverflow.com/questions/65880540/how-find-entities-for-each-row-of-a-big-data

Answer 1

Waitting for answers