• Source code of slides
• Introduction to CLTK

1. How to import a corpus
2. How to tokenize a text
3. How to syllabify a text
4. How to lemmatize a text
5. How to tag a text with parts-of-speech
6. How to tag a text with named-entities

• Retrieving complete text
• Reading the annotated texts
• How to train a lemmatizer, a POS (parts-of-speech) tagger with an annotated corpus

• Making an approximately TEI compliant text from a website with heimskringla.no
• Retrieving Völsunga saga from a Python package

• Observing characters sets

• See how to read an other annotated corpus

• I want to run a notebook without downloading a repository: You can click on such a button in READMEs (if there is one) or you launch it yourself with mybinder.org.

• I want to install CLTK: pip install cltk and you get the last released version of CLTK.

• I want to become a contributor: you can read the following instructions.

• Ok, what you show here is good, but it's not enough, I want an other tutorial: you can check our wiki out.

• What can CLTK do? It's here.

By Clément Besnier and Eleftheria Chatziagyriou