Tutorials for the Natural language processing course (UL FRI - Digital Linguistics)

^{This repository is a modified version (intended for digital linguistics students) of the original repository of Natural Language Processing course at the University of Ljubljana, Faculty for computer and information science. It contains additional resources and materials to supplement the original work plan. Please contact ales.zagar@fri.uni-lj.si for any comments.}

Environment Preparation

• Read tutorial basics.md on how to install a virtual environment
• Goal: Learn to create a virtual environment

Basic Text Processing

• Solve notebook basic-text-processing.ipynb
• Goal: Practice text processing

Repository Management

• Read git basics git.md
• During the labs, we will be working through the exercises
• Goal: Learn how to collaborate with colleagues using a remote code repository

Data Wrangling

• Together we will work through the notebook data-wrangling-demo-solutions.ipynb
• Solve notebook data-wrangling-exercise.ipynb
• Goal: Learn to process and manipulate data

Basics of Machine Learning

• Together we will work through the notebook machine-learning-basics.ipynb
• Solve the exercise at the end of the notebook
• Goal: Get familiar with classification, regression, and clustering

How to run classla

CLASSLA 2.2 needs an old version of numpy! Therefore, to run this notebook, please use python 3.10. To run this notebook, please use e.g. the following commands:

conda create -n nlp-classla python=3.10
pip install classla