spacy_sentence_with_abbreviations.py

import spacy
from spacy.attrs import ORTH, LEMMA

text = 'Sgt. Maj. A. Grinston found approx. 2.2 miles up a creek on Mt. Toohigh.'

nlp = spacy.load('en_core_web_lg')

print([t.text for t in nlp(text).sents])
#=> ['Sgt.', 'Maj.', 'A. Grinston found approx.', '2.2 miles up a creek on Mt. Toohigh.']

nlp.tokenizer.add_special_case('Sgt.', [{ORTH: 'Sgt.', LEMMA: 'seargeant'}])
nlp.tokenizer.add_special_case('Maj.', [{ORTH: 'Maj.', LEMMA: 'major'}])
nlp.tokenizer.add_special_case('approx.', [{ORTH: 'approx.', LEMMA: 'approximately'}])

print([t.text for t in nlp(text).sents])
#=> ['Sgt. Maj. A. Grinston found approx. 2.2 miles up a creek on Mt. Toohigh.']