分塊是根據(jù)單詞的性質(zhì)將相似單詞分組在一起的過程。 在下面的示例中，我們定義了必須生成塊的語法。 語法表示在創(chuàng)建塊時將遵循的諸如名詞和形容詞等短語的序列。 塊的圖形輸出如下所示。

import nltk

sentence = [("The", "DT"), ("small", "JJ"), ("red", "JJ"),("flower", "NN"), 
("flew", "VBD"), ("through", "IN"),  ("the", "DT"), ("window", "NN")]
grammar = "NP: {?
*}" 
cp = nltk.RegexpParser(grammar)
result = cp.parse(sentence) 
print(result)
result.draw()

當(dāng)運行上面的程序時，我們得到以下輸出 -

改變語法，我們得到一個不同的輸出，如下代碼所示 -

import nltk

sentence = [("The", "DT"), ("small", "JJ"), ("red", "JJ"),("flower", "NN"),
 ("flew", "VBD"), ("through", "IN"),  ("the", "DT"), ("window", "NN")]

grammar = "NP: {
?*}" 

chunkprofile = nltk.RegexpParser(grammar)
result = chunkprofile.parse(sentence) 
print(result)
result.draw()

如下所示 -

Chinking

Chinking是從塊中移除一系列令牌的過程。 如果令牌序列出現(xiàn)在塊的中間，則刪除這些令牌，留下兩個已經(jīng)存在的塊。

import nltk

sentence = [("The", "DT"), ("small", "JJ"), ("red", "JJ"),("flower", "NN"), ("flew", "VBD"), ("through", "IN"),  ("the", "DT"), ("window", "NN")]

grammar = r"""
  NP:
    {<.*>+}         # Chunk everything
    }+{      # Chink sequences of JJ and NN
  """
chunkprofile = nltk.RegexpParser(grammar)
result = chunkprofile.parse(sentence) 
print(result)
result.draw()

當(dāng)運行上面的程序時，我們得到以下輸出 -

如所所示，符合語法標(biāo)準(zhǔn)的部分從名詞短語中省略為單獨的塊。 提取不在所需塊中的文本的過程稱為chinking。