This repository has been archived by the owner on May 5, 2021. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 320
pipeline for no-whitespace language #693
Comments
You should be able to use the JiebaTokenizer. However it is not installed by default in Rasa. So you need to add it explicitly to the requirements of the Rasa image built in your Botfront project |
@znat |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
When create a project , the default tokenize in pipeline is WhitespaceTokenizer,
if my project is base on no-whitespace language(ie:chinese, japanese),
How should I set the pipeline?
Or I didi not need to modify the default pipeline?
The text was updated successfully, but these errors were encountered: