dac.py 文件源码

def set_entity_match(self):
        '''
        Match other entities appearing in the article with DBpedia abstract.
        '''
        if not 'match_txt_entities' in self.features:
            return

        if not hasattr(self.cluster, 'entity_parts'):
            self.cluster.get_entity_parts()
        if not hasattr(self.cluster, 'context_entity_parts'):
            self.cluster.get_context_entity_parts()
        if not self.cluster.context_entity_parts:
            return

        if not hasattr(self, 'abstract_bow'):
            self.tokenize_abstract()
        bow = [t for t in self.abstract_bow if len(t) > 4]

        entity_match = len(set(self.cluster.context_entity_parts) & set(bow))
        self.match_txt_entities = math.tanh(entity_match * 0.25)