CLAPS
CLAPS copied to clipboard
[ICLR 2021] Contrastive Learning with Adversarial Perturbations for Conditional Text Generation
Hello seanie, I'm very interested with your "ADVERSARIAL PERTURBATIONS", but i'm not very sure about the influence of self.zero_grad() in the functions of models.py. May I ask about why it...
Hi, seanie. Your paper is interesting, and I want to try your method for other text generation tasks. However, I am confused about some points in your paper: 1. How...
labels = torch.arange(batch_size, device=input_ids.device) cont_loss = cont_crit(logits, labels) new_cont_loss = cont_crit(new_logits, labels) Hello! Look at your work and feel very good! So I tried to learn, in the process of...