自然语言处理(NLP) 二：词形还原 + 词块划分

1、词形还原

名字：复数->单数
动词：分词->原型

import nltk.stem as ns

words = ['table','probably','wolves','playing','is','dog','the','beaches','grounded','dreamt','envision']

lemmatizer = ns.WordNetLemmatizer()
for word in words:
    lemma = lemmatizer.lemmatize(word,'n')
    print(lemma)
print('-'*72)
for word in words:
    lemma = lemmatizer.lemmatize(word,'v')
    print(lemma)

2、词块划分

import nltk.corpus as nc 
doc = ' '.join(nc.brown.words()[:310])
print(doc)
words = doc.split()
print(words)
chunks = []
for word in words:
    if len(chunks) == 0 or len(chunks[-1])==5:
        chunks.append([])
    chunks[-1].append(word)
for chunk in chunks:
    for word in chunk:
        print('{:15}'.format(word),end='')
    print()