shuangqinbuaa

How should I preprocess the data?

8

If I just want to train the SCPN model, I just need to preprocess the para-nmt dataset. But what if I want to use SCPN to generate syntactically adversarial examples...

Questions about training time consuming

2

I try to train the scpn model but the training data is too large. I use one GPU. The batch size is 64 and for every batch I need 1.6...

Some questions about trans_embs

3

Hello, thank you so much for sharing the code with us. I have learned a lot. Thank you so much! But I have some questions about the trans_embs in this...

The line 241 in train_scpn.py: copy_probs = copy_probs.view(-1); I think it should be: copy_probs = copy_probs.transpose(0, 1).contiguous().view(-1) because decoder_states, decoder_copy_dists are transposed: line 234: decoder_states = decoder_states.transpose(0, 1).contiguous().view(-1, self.d_hid *...