Training data format for Urdu

I have training data in Urdu language and since Urdu is written from right-to-left. I am having trouble in labeling the entity names that are in English. For example.

intent:inform

  • چک شہزاد میں حادثہ ہوا ہے

I want the substring چک شہزاد to be labelled like this میں حادثہ ہوا ہے (location)[چک شہزاد]

is this the correct way to do this?

I have this problem in Persian … could somebody help? tanx

1 Like

Yes, check this repository GitHub - mirfan899/ubot: Code of tutorial https://www.urdunlp.com/2020/04/building-conversational-chat-bot-for.html