vocabulary.py 文件源码

def __init__(self, train_sents): # [_code-unigram-chunker-constructor]
        train_data = [[(t,c) for w,t,c in nltk.chunk.tree2conlltags(sent)]
                      for sent in train_sents]
        self.tagger = nltk.BigramTagger(train_data) # [_code-unigram-chunker-buildit]