This section is not strictly related to machine learning, but it contains some machine learning results in the area of natural language processing. Python has many packages to process text data, and one of most powerful and complete toolkit for text processing is NLTK, the Natural Language Tool Kit.
Other NLP toolkits available for the Python community are gensim (https://radimrehurek.com/gensim/) and spaCy (https://spacy.io/)
In the following sections, we'll explore NLTK core functionalities. We will work on the English language; for other languages, you will first need to download the language corpora (note that sometimes languages have no free open source corpora for NLTK).
Please refer to the official website of NLTK data, http://www.nltk.org/nltk_data/, to have access to corpora and lexical resources in many languages, ready...
