Implementation of our papers Joint entity recognition and relation extraction as a multi-head selection problem (Expert Syst. Appl, 2018) and Adversarial training for multi-context joint entity and relation extraction (EMNLP, 2018).
when I set batchsize=16 or other num, raise error"ValueError: setting an array element with a sequence."in
"""
_, val, predicted_ner, actual_ner, predicted_rel, actualrel, , m_train = self.sess.run(
[operations.train_step, operations.obj, operations.predicted_op_ner, operations.actual_op_ner, operations.predicted_op_rel, operations.actual_op_rel, operations.score_op_rel,
operations.m_op], feed_dict=x_train)
"""
how can i fix it?
do you know how to set batchsize? If the batchsize is not 1, it seems that padding will affect the calculation of relationships. How can we remove the effect of padding?
when I set batchsize=16 or other num, raise error"ValueError: setting an array element with a sequence."in """ _, val, predicted_ner, actual_ner, predicted_rel, actualrel, , m_train = self.sess.run( [operations.train_step, operations.obj, operations.predicted_op_ner, operations.actual_op_ner, operations.predicted_op_rel, operations.actual_op_rel, operations.score_op_rel, operations.m_op], feed_dict=x_train) """ how can i fix it?