Split examples

This commit is contained in:
Andras Schmelczer 2022-05-25 22:54:21 +02:00
parent b4492da2e6
commit df1c9418ee
No known key found for this signature in database
GPG key ID: 39260B5B0614A13E
11 changed files with 401 additions and 252 deletions

View file

@ -1,8 +0,0 @@
import re
from great_ai.utilities.lemmatize_text import lemmatize_text
def preprocess(text: str) -> str:
lemmas = [re.sub(r"\d[\d.,]*", "NUM", lemma) for lemma in lemmatize_text(text)]
return " ".join(lemmas)