corpus.py 文件源码

def save_data(self, preprocess, max_len, qid, q1, q2, label):
        if preprocess:
            q1 = preprocess_sentence(q1, max_len)
            q2 = preprocess_sentence(q2, max_len)
        # This is a non-duplicate sentence -> dissimilar
        if label == '0':
            self._non_sim_data.append(Data(qid, q1, q2, label, [0, 1]))
        # This is a duplicate sentence -> similar
        else:
            self._sim_data.append(Data(qid, q1, q2, label, [1, 0]))