testers/bleu-4.py

from nltk.translate.bleu_score import sentence_bleu

reference = [
    'this is a dog'.split(),
]

candidate = 'this is dog'.split()

# quanto la frase candidata è vicina a quelle di riferimento
print('Individual 1-gram: %f' % sentence_bleu(reference, candidate, weights=(1, 0, 0, 0)))
print('Individual 2-gram: %f' % sentence_bleu(reference, candidate, weights=(0, 1, 0, 0)))
print('Individual 3-gram: %f' % sentence_bleu(reference, candidate, weights=(0, 0, 1, 0)))
print('Individual 4-gram: %f' % sentence_bleu(reference, candidate, weights=(0, 0, 0, 1)))

print('average 4-gram: %f' % sentence_bleu(reference, candidate, weights=(0.25, 0.25, 0.25, 0.25)))