Skip to content

关于pretraining时denoising的问题 #71

Description

@tu2022

我看bart的论文在pretraining的时候会有五种denoising的方法,在bart_dataset.py中我看insert_ratio和rotate_ratio是设为0,似乎不能将其设为大于0的数,是否意味着不能进行text infilling和rotation?

Activity

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

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions