np_extractors.py 文件源码

def train(self):
        '''Train the Chunker on the ConLL-2000 corpus.'''
        train_data = [[(t, c) for _, t, c in nltk.chunk.tree2conlltags(sent)]
                      for sent in
                      nltk.corpus.conll2000.chunked_sents('train.txt',
                                                    chunk_types=['NP'])]
        unigram_tagger = nltk.UnigramTagger(train_data)
        self.tagger = nltk.BigramTagger(train_data, backoff=unigram_tagger)
        self._trained = True