Thanks to visit codestin.com
Credit goes to github.com

Skip to content

How to handle tokens during the tokenization process that did not appear in the training set? #140

@MasterBeard

Description

@MasterBeard

This is an excellent article. I have one question: how to handle tokens during the tokenization process that did not appear in the training set? Due to some extreme events in time series, it's likely that some tokens in the test set may not have appeared in the training set.

Metadata

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