spaCy/spacy/lang/it/tokenizer_exceptions.py
2019-08-20 17:36:34 +02:00

8 lines
167 B
Python

# coding: utf8
from __future__ import unicode_literals
from ...symbols import ORTH, LEMMA
_exc = {"po'": [{ORTH: "po'", LEMMA: "poco"}]}
TOKENIZER_EXCEPTIONS = _exc