An Introductory Python course for Computational Lingustics.
Title | Colab | Binder | |
---|---|---|---|
1.1 | About the Course | ||
1.2 | Introduction to Python | ||
1.3 | Basic NLP with Python | ||
1.4 | Working with Corpus Data |
Title | Colab | Binder | |
---|---|---|---|
2.1 | Naive Bayes | ||
2.2 | Sentiment Analysis | ||
2.3 | POS Tagging |
Note: this applies ONLY if you plan to run the course locally on your own machine. For now, we recommend accessing the course materials with Colab or Binder (see above).
For this project we will use Python 3.6+. The project structure is:
.
├── CONTRIBUTING.md
├── corpora
├── LICENSE
├── module_1
│ ├── module_1.1
│ ├── ...
│ └── module_1.4
├── ...
├── module_4
├── README.md
├── requirements.txt
├── resources
└── Templates
You should look into the folders module_x
. Each module is divided in many submodules, and each module_x.y folder
contains the the Jupyter notebooks you will run during the course. The folder corpora
contains the corpora you will use for this course.
The other resources contained in the present repository are:
README.md
is the present file;requirements.txt
contains all the Python libraries required to run the code. You will use this file when installing Python libraries on your machine;- The file
CONTRIBUTING.md
and the foldersTemplates
andresources
contain the guidelines and the resources we used to write this course. LICENSE
contains a copy of the CC BY-NC 4.0 License.
The content in this repository is released under the CC BY-NC 4.0 license.
The icons used are made by Freepik from www.flaticon.com and are licensed with a CC 3.0 BY permissive license.