Dual-Contrastive-Learning
Dual-Contrastive-Learning copied to clipboard
Published
20 hours ago •
hiyouga
hiyouga
For the labels containing multiple words, How to take the mean-pooling?
For the labels containing multiple words, How to take the mean-pooling? Is there this code in files?
There are two approaches to tackling this problem. We can take the mean-pooling on the BERT outputs to obtain the label representations. Alternatively, we can also take the first word in the label if it does not conflict with other labels.
