Natural Language Processing (NLP) — teaching computers to understand human language through simple, friendly guides.

Start Here — Introduction to NLP:

1. NLP - A Friendly Introduction - What is NLP, where it’s used, linguistic levels, the pipeline, and different approaches

Lexical Processing (Breaking Down Words):

1. Lexical Processing - A Friendly Guide - Tokenisation, text normalisation, stemming, lemmatisation, stopwords, and spell correction

Syntactic Processing (Understanding Structure):

1. Syntactic Processing Part 1 - POS Tagging and Shallow Parsing - Part-of-Speech tagging and chunking words into phrases

2. Syntactic Processing Part 2 - Context-Free Grammar and Parsing - Grammar rules, constituency and dependency parsing

3. Syntactic Processing Part 3 - Tree Structures and Grammatical Agreement - Parse trees and ensuring grammatical correctness

Semantic Processing (Understanding Meaning):

1. Semantic Processing Part 1 - Word Meaning and Disambiguation - Lexical semantics, WordNet, word sense disambiguation, co-occurrence models, and Pointwise Mutual Information (PMI)

2. Semantic Processing Part 2 - Entities, Roles, and Coreference - Semantic Role Labelling, Named Entity Recognition, IOB tagging, Conditional Random Fields, and Coreference Resolution

Text Representation and Unsupervised Modelling:

1. Text Representation and Unsupervised Modelling - Bag-of-Words, TF-IDF, Word Embeddings (Word2Vec/GloVe), and Topic Modelling with NMF

Classical Text Generation:

1. Classical Text Generation Part 1 - Language Models and Markov Chains - N-gram language models, Markov chains, smoothing techniques, and perplexity

2. Classical Text Generation Part 2 - Summarisation and Translation - Sentence generation strategies (beam search, temperature), extractive summarisation (TextRank), and statistical machine translation

Applying ML to NLP:

1. Machine Learning with NLP - A Friendly Guide - How machine learning transforms text into predictions (sentiment analysis, classification, NER)

Quick Reference:

1. NLP Cheat Sheet - Key Terms and Concepts - Every important NLP term with plain-English definitions, memory aids, comparison tables, and the full pipeline at a glance

2. NLP Libraries - Python Toolkit Reference - Complete guide to NLTK, spaCy, scikit-learn, gensim, TextBlob, sumy, and sklearn-crfsuite — with install instructions and ready-to-run code for every task

Learning Path:

Start with the Introduction to understand the big picture, then move through Lexical Processing to learn how computers break down text. Continue with Syntactic Processing (Parts 1-3) for sentence structure. Explore Semantic Processing (Parts 1-2) for meaning and entities. Learn how to represent text as numbers in Text Representation. Then see how classical systems generate, summarise, and translate text. Finally, see how ML with NLP builds practical applications on top of all these foundations.

All guides use friendly explanations, real-world examples, and working Python code you can run yourself.