Miteiru, Shunou, Utatteiru

This post is going to be my research point on how I develop three of the ambitious personal projects I wanna make. Shunou is a service, and uses MeCab.

References:

• https://www.dampfkraft.com/nlp/how-to-tokenize-japanese.html
• https://www.dampfkraft.com/nlp/japanese-tokenizer-dictionaries.html
• https://towardsdatascience.com/how-japanese-tokenizers-work-87ab6b256984

As per Dec, 27^th 2022, I haven’t thought of any good service to deploy this Shunou on yet. It depends heavily on MeCab, which I have no idea on how to pack the app into the service. My best bet, is to use Docker and proceed to install the mecab inside. Thus, it should be pretty heavy when running the container.