feature_construction.py 文件源码

def _identify_pronoun2(self, sentence):
        """Calculate percentage of pronouns in the sentence that are in the answer
        - Args:
            sentence(str): question sentence 
        - Returns:
            pronoun_in_sentence(list): pronouns in sentence 
            sentence_len(int): length of current sentence 
        """
        text = nltk.word_tokenize(sentence)
        post = nltk.pos_tag(text)
        pronoun_list = ['PRP', 'PRP$', 'WP', 'WP$']
        pronoun_in_sentence = []
        sentence_len = len(post)
        for k, v in post:
            if v in pronoun_list:
                pronoun_in_sentence.append(k)
        return pronoun_in_sentence, sentence_len