Does anyone know the difference between nltk\'s wordpunct_tokenize and word_tokenize? I\'m using nltk=3.2.4 and there\'s noth
nltk
wordpunct_tokenize
word_tokenize
nltk=3.2.4
Word_tokenize is for tokenizing a word in a sentence while wordpunct_tokenize is to remove the non-English words in a sentence.
Word_tokenize