Nothing quite that advanced. It’s mostly just stemming, basic tokenization, TF-IDF, and cosine similarity at this point.

I’ll second Rustlings as a great learning experience. I haven’t had a chance to try it out, but The Book now has a link to a more interactive version that looks great.

I started working on a text analysis crate during grad school. I’ve gotten some surface-level stuff in there already, but I’d like to flesh it out and add some more true NLP functionality.

Link: https://github.com/michael-long88/rnltk