embedding of relations are multiplied by rel_matrix, which seems wrongly implemented.
pos_r_e is of shape [batchSize, sizeR] , matrix is of shape [batchSize, sizeE, sizeR], tf.batch_matmul(matrix, neg_r_e) cannot be computed unless sizeE = sizeR, but this assumption isn't always true.
In transR's original paper , relation's embedding does not need to be multiplied by some matrix.
transR.py script will crash if you set hidden_sizeE != hidden_sizeR
in transR.py line 59 and line 62
embedding of relations are multiplied by rel_matrix, which seems wrongly implemented. pos_r_e is of shape [batchSize, sizeR] , matrix is of shape [batchSize, sizeE, sizeR], tf.batch_matmul(matrix, neg_r_e) cannot be computed unless sizeE = sizeR, but this assumption isn't always true. In transR's original paper , relation's embedding does not need to be multiplied by some matrix.
transR.py script will crash if you set hidden_sizeE != hidden_sizeR