koaning / tokenwiser

Bag of, not words, but tricks!
https://koaning.github.io/tokenwiser/
Apache License 2.0
68 stars 7 forks source link

Remove text based on proba property in spaCy. #34

Closed koaning closed 2 years ago

koaning commented 3 years ago

It's a stopwords removal component based on the information given from spaCy lookup tables. Could be a nice textprep component.