This repository contains Jupyter notebooks for exercise sheets based on the "Natural Language Toolkit (NLTK)" book, a popular guide for learning and applying Natural Language Processing (NLP) in Python.
Each notebook corresponds to an exercise sheet focusing on different aspects of NLP, demonstrating practical applications and exercises for mastering the NLTK framework.
Summary: Introduces basic NLP concepts using NLTK, including word counts and lexical diversity calculations.
Summary: Focuses on improving Python code efficiency by rewriting loops as list comprehensions, with applications in NLP tasks.
Summary: Explores the Brown corpus in NLTK, teaching how to sort and understand both original and universal part-of-speech tags.
Summary: Involves building a name gender classifier using the Names Corpus in NLTK, covering feature extraction, Naive Bayes Classifier application, and model evaluation.
To work with these notebooks, you'll need Python 3.x, NLTK, and Jupyter Notebook. Install them using pip:
pip install nltk jupyter
Clone this repository and run the Jupyter notebooks locally:
jupyter notebook