This repository is an open-source NLP introductory book (一本开源的NLP入门书籍) covering fundamental NLP techniques including Word2Vec and Doc2Vec for text representation, FastText and multilayer perceptrons for document classification, LDA for topic modeling, TextRank and TFIDF for keyword extraction, and document similarity measurement. It also includes practical applications such as sentiment analysis on Yelp reviews and security-focused NLP use cases like spam detection and content moderation.