Lemmatisation reduces a word to its lemma,

Lemma is "a heading indicating the subject or argument of a literary composition or annotation."

To lemmatise in python,

from nltk.stem.wordnet import WordNetLemmatizer
lmtz = WordNetLemmatizer()
lmtz.lemmatize('words')

To tokenise a word,

from nltk.tokenize import word_tokenize
word_tokenize('hi how are you?')