I would like to extract bank names from a given text like wells Fargo, chase....is there a python library for this? I know there is entity tagger in space and flair but they only identify the entity (org/person)
$\begingroup$
$\endgroup$
1
-
2$\begingroup$ Have you tried creating a list of bank names and using the regex python module to extract the bank names from the text $\endgroup$– Anoop A NairDec 14, 2020 at 14:47
Add a comment
|
2 Answers
$\begingroup$
$\endgroup$
As mentioned in the comment you can use regex but you would need to define a set of rules for it. You can try with LexNLP which is trained on legal documents and use it to extract data type like address, companies and persons.
answered Dec 16, 2020 at 8:12
$\begingroup$
$\endgroup$
1
It might be solved with Name Entity Recognition
There you go an example using spacy. I highly recommend you to check its documentation.
The disadvantage of this approach is that it might be computationally expensive and time-consuming
import spacy
nlp = spacy.load("en_core_web_sm")
doc = nlp("Apple is looking at buying U.K. startup for $1 billion")
for ent in doc.ents:
print(ent.text, ent.start_char, ent.end_char, ent.label_)
-
$\begingroup$ I tried lg model as well. Too many false positives. Try this give Xxxx xxx, this will be classified as person. Not sure what exactly the algo logic is $\endgroup$ Dec 16, 2020 at 15:49