Skip to content

For the labels containing multiple words, How to take the mean-pooling? #11

Open
@TianlinZhang668

Description

For the labels containing multiple words, How to take the mean-pooling? Is there this code in files?

Activity

hiyouga

hiyouga commented on Nov 8, 2022

@hiyouga
Owner

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.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions

      For the labels containing multiple words, How to take the mean-pooling? · Issue #11 · hiyouga/Dual-Contrastive-Learning