elte-nlp / elte-nlp-course

NLP & FM Lecture Slides
https://drive.google.com/drive/u/1/folders/1S_WgFtfvz-Tw1a7TMupgg0s2GoO_0ZHv
Creative Commons Attribution 4.0 International
31 stars 2 forks source link

Tokenization #2

Closed DavidNemeskey closed 1 year ago

DavidNemeskey commented 1 year ago

Made a few changes to the tokenization slides + added all references at the end. I have not created a new PDF, as even creating a new branch is 45MB with all these PDFs! We should definitely store them somewhere else...

andras-simonyi commented 1 year ago

Thanks! As for the pdfs, what do you think about storing the latest relevant versions somewhere else (say, in some kind of public shared folder)? (Building and uploading would be done manually at first but could be automated with GitHub actions later on.)