Getting Started with Natural Language Processing

This repository accompanies the book Getting Started with Natural Language Processing available here. Here you will also find an NLP course that uses this book.

To get a 42% discount on the book, use the coupon code "slkochmar" .

• Chapter 1 – Introduction
• Chapter 2 – Your first NLP example
• Chapter 3 – Introduction to Information Search
• Chapter 4 – Information Extraction
• Chapters 5 & 6 – Author Attribution and User Profiling
• Chapters 7 & 8 – Sentiment Analysis
• Chapter 9 – Topic Analysis
• Chapter 10 – Topic Modeling
• Chapter 11 – Named Entity Recognition

Installation Instructions

To run the notebooks on your machine, check if Python 3 is installed (all code was written and tested with Python 3.7). In addition, you will need the following libraries (notebooks tested with the versions indicated in the brackets):

• NLTK (v 3.5): check installation instructions for the toolkit at https://www.nltk.org/install.html and the accompanying data at https://www.nltk.org/data.html
• SpaCy (v 3.1.3): check installation instructions at https://spacy.io/usage. You will also need to install models (e.g., en_core_web_sm, en_core_web_md, and en_core_web_lg) using the instructions on the website.
• Gensim (v 3.8.0): check installation instructions at https://radimrehurek.com/gensim/
• Matplotlib (v 3.1.3): check installation instructions at https://matplotlib.org/users/installing.html
• Scikit-learn (v 0.22.1): check installation instructions at http://scikit-learn.org/stable/install.html
• NumPy (v 1.18.1): check installation instructions at https://www.scipy.org/install.html
• Pandas (v 1.0.1) check installation instructions at https://pandas.pydata.org/pandas-docs/stable/getting_started/install.html

Alternatively, a number of these libraries can be installed in one go through Anaconda distribution.

For more information on Jupyter notebooks, check https://jupyter.org.