one question about top_antecedent_cluster_ids
Opened this issue · 0 comments
MENGHAH commented
in coref_model.py
top_antecedent_cluster_ids = tf.gather(top_span_cluster_ids, top_antecedents)
top_antecedent_cluster_ids += tf.to_int32(tf.log(tf.to_float(top_antecedents_mask)))
The first step have got the top_antecedent_cluster_ids,why does there still run the second step?