.. _sec-nlp-refs:

References for further study
============================

NLP is a vast field of study with a broad scope, and it can be quite challenging for beginners to know where to start or which concepts are the most important to understand. In this section, we provide a few references for further study.

Reading
-------
For beginners interested in learning more about NLP, apart from this tutorial there are many online resources available. Some good starting points include:

- The `NLTK book <https://www.nltk.org/book/>`_ provides an introduction to NLP with Python.
- Another great resource for beginners interested in NLP is the book "Speech and Language Processing" by Jurafsky and Martin. This textbook provides a comprehensive introduction to NLP, covering topics such as language modelling, part-of-speech tagging, syntax and parsing, and machine translation. The book is available online for free `here <https://web.stanford.edu/~jurafsky/slp3/>`_. In addition to the book itself, the website provides supplementary materials, such as lecture slides and programming exercises, that can help readers deepen their understanding of the material.
- The article `A beginner's guide to natural language processing <https://developer.ibm.com/articles/a-beginners-guide-to-natural-language-processing/>`_ on the `IBM Developer <https://developer.ibm.com>`_ website provides a high-level overview of NLP and its importance in machine learning, covering topics such as text preprocessing, feature extraction, and model selection.
- The article of Stanford Encyclopedia of Philosophy on the broader area of `computational linguistics <https://plato.stanford.edu/entries/computational-linguistics/>`_.

Online courses
--------------
- The `Coursera NLP Specialization course <https://www.coursera.org/specializations/natural-language-processing>`_ covers a wide range of topics in NLP with video lectures and hands-on assignments.

Organisations
-------------
- The `Stanford NLP group <https://nlp.stanford.edu/>`_ provides a wealth of resources, including research papers, datasets, and open-source software.

Software tools
--------------
- `Natural Language Toolkit (NLTK) <https://www.nltk.org>`_
- `PyTorch <https://pytorch.org>`_
- `TensorFlow <https://www.tensorflow.org>`_