NLP Workshop | Tooploox & Grupa Pracuj

About this repo

• ./notebooks - practical examples (to run them install requirements.txt)
• ./data - here you can find the data that will be used throughout the workshop
• ./src - helper functions (mostly data gathering)
• ./docker - Dockerfiles for Morfeusz and MACA / krnnt (for working with Polish language)

Data

We store large files with Git LFS. To download all data used in this tutorial you need to have Git LFS installed. Then, after cloning the repo, run the following.

git lfs pull

Syllabus

• Google drive with lecture notes

Week 1

1. Intro, around the NLP
2. Text Normalization and RegEx
3. LDA

Week 2

1. Lemma, PoS, dependency-parsing
2. Lemmatization in Polish (morfeusz)
3. BoW models
4. word2vec

Week 3

1. Introduction to neural networks
2. RNNs
3. LSTMs