Dual-Contrastive-Learning
Dual-Contrastive-Learning copied to clipboard
hiyouga
Code for our paper "Dual Contrastive Learning: Text Classification via Label-Aware Data Augmentation"
Your work is very good and effective. But I have some questions about the baseline approach. I tried different hyperparameters to adjust supervised contrastivelearning or unsupervised contrastive learning to fine-tune...
Using the calculation comparison loss method in the source code, the calculated loss may be negative, My input is（batchsize*dim, batchsize*class_num*dim, class_num）,And Lz and Lθ may be negative at the same...
It's a great job. But I have a question, why do you use DualCL to perform out-of-order operation specifically for labels? This operation will not change the real label in...
Hi, thank you for your exciting work. When I want to save model get this error: Transformer object has no "save_pretrained" How to save the model after we train it...
Hi thank you for your exciting work. I've noticed a potential problem regarding to the evaluation procedure. To best of my knowledge currently the best model is selected based on...
hello author If the model runs on the Chinese dataset，What parts need to be modified and What should be paid attention to？ thank you！
Hi there! I think these code and paper awesome! when I run this code, I can see increasing accuracy. but I want to see moving that the class representation and...
For the labels containing multiple words, How to take the mean-pooling? Is there this code in files?
Dear author, your framework is valid on the English dataset, but when I used dual-loss deficiency on my Chinese dataset, gradient collapse occurred. My Chinese label is two characters, is...
