np_extractors.py 文件源码

def train(self):
        train_data = nltk.corpus.brown.tagged_sents(categories='news')
        regexp_tagger = nltk.RegexpTagger([
            (r'^-?[0-9]+(.[0-9]+)?$', 'CD'),
            (r'(-|:|;)$', ':'),
            (r'\'*$', 'MD'),
            (r'(The|the|A|a|An|an)$', 'AT'),
            (r'.*able$', 'JJ'),
            (r'^[A-Z].*$', 'NNP'),
            (r'.*ness$', 'NN'),
            (r'.*ly$', 'RB'),
            (r'.*s$', 'NNS'),
            (r'.*ing$', 'VBG'),
            (r'.*ed$', 'VBD'),
            (r'.*', 'NN'),
            ])
        unigram_tagger = nltk.UnigramTagger(train_data, backoff=regexp_tagger)
        self.tagger = nltk.BigramTagger(train_data, backoff=unigram_tagger)
        self._trained = True
        return None