Rasa is also good for languages other than English?

Hi All again,

I plan to build a chatbot for Korean language in the area of tourism using RASA.

I heard that RASA is language-independent. But has anyone tried to use RASA for languages other than English? Are there any difficulties that I have to know before using RASA? Thank you!


As mentioned in our documentation, you can use Rasa with other languages than English. We know that there are bots out there in Spanish, Japanese, or Russian, for example.

In order to understand what the user is saying, you need to define a pipeline (Choosing a Pipeline). As spacy does not provide any Korean model out of the box, I would recommend that you use the supervised_embeddings pipeline. However, not sure if you can use the WhitespaceTokenizer for Korean. If you cannot tokenize the text using that tokenizer, you might need to write something on your own (Custom NLU Components). Hope that get’s you started!


Thank you so much! I’ll check the pages first :slight_smile: