Second assignment of the course of Natural Language Understanding.
The following Python libraries are required:
- spacy (version 3)
- nltk
- scikit-learn
- pandas
- operator
The English model en_core_web_sm
of spaCy is also required and can be downloaded running the command:
python -m spacy download en_core_web_sm
The source code file is a Jupyter notebook and can be executed with Jupyter or Google Colab. Documentation and description of the code is present in the notebook.
The data
folder contains a subfolder conll2003
that contains training and test dataset of CoNLL 2003.
The file conll.py
is located in root folder.