This repository provides hands-on tutorials for learning Natural Language Processing through deep learning. It covers foundational embedding models (NNLM, Word2Vec, FastText), convolutional networks (TextCNN), sequence models (RNN, LSTM, Seq2Seq), attention mechanisms, and transformer architectures including BERT. Each model is implemented in PyTorch within approximately 100 lines of code for beginner readability, with links to original papers and Google Colab notebooks.