Why we need to expand and reshape the tensor to [(slot_dim*ds*ts), bert_seq, hid_size]

[yixuan004]

Why we need to expand and reshape the tensor to [(slot_dimdsts), bert_seq, hid_size], is that mean every utterance need to mapping into slot_dim times prediction https://github.com/SKTBrain/SUMBT/blob/011127be0587f942e95b6dd8e6e15195577a637c/code/BeliefTrackerSlotQueryMultiSlot.py#L214

[yixuan004]

My code base is weak, hope to get your help! Thanks!