feature_construction.py 文件源码

def _identify_pronoun(self, answer):
        """Calculate percentage of pronouns within answer
        - Args:
            answer(str): answer text
        - Returns:
            percentage(float): ratio of pronouns in answer
        """
        text = nltk.word_tokenize(answer)
        post = nltk.pos_tag(text)
        pronoun_list = ['PRP', 'PRP$', 'WP', 'WP$']
        # init variables
        num_pronouns = 0
        num_terms = len(post)
        percentage = 0
        for k, v in post:
            if v in pronoun_list:
                num_pronouns += 1
        percentage = float(num_pronouns) / num_terms
        return percentage