Hi all,
I am Joseph and am just starting out using Rasa to build a Chinese customer service chatbot for my company. I am stuck because I am not sure if I need to download any pretrained Chinese word vectors or can I just use my own conversation data, and how can I do it?
Thank you.
You can use your own data, however you will still need a different tokenizer for Chinese. You would also need a lot of data in order to make this better. I would recommend the Jieba-MITIE language model with the mitie pipeline.
Continuing the discussion from Chinese bot:
Hi, Ella. It is indicated that the MITIE is likely to be deprecated in the future. How should I do it, if MITIE pipeline being removed?
hello，I am also building a Chinese bot，but I am a freshman in rasa. How is your progress? Thank You