Spacy настраивает сегментацию предложений
#ADD A NEW RULE TO THE PIPELINE
def set_custom_Sentence_end_points(doc):
for token in doc[:-1]:
if token.text == ';':
doc[token.i+1].is_sent_start = True
return doc
#ADD A NEW RULE TO THE PIPELINE
def set_custom_Sentence_end_points(doc):
for token in doc[:-1]:
if token.text == ';':
doc[token.i+1].is_sent_start = True
return doc