一、Chunking 句子分块

Segmentation and Labeling at both the Token and Chunk Levels

1 noun phrase chunking( NP-chunking)名词短语

import nltk

sentence = [("the", "DT"), ("little", "JJ"), ("yellow", "JJ"),("dog", "NN"), ("barked", "VBD"), ("at", "IN"),  ("the", "DT"), ("cat", "NN")]

grammar = "NP: {<DT>?<JJ>*<NN>}"

cp = nltk.RegexpParser(grammar)

result = cp.parse(sentence)

print(result)

result.draw()

----------------------------------------------------------

如果觉得上述对句子人式标注很麻烦，可以改为以下：

import nltk

sentence="the little dog baked at the cat"

words=nltk.word_tokenize(sentence)   #分词

sent_tag=nltk.pos_tag(words)       #加标注

grammar = "NP: {<DT>?<JJ>*<NN>}"

cp = nltk.RegexpParser(grammar)

result = cp.parse(sent_tag)

print(result)

result.draw()

练习1：考虑下面的名词短语如何表示。