nlp-tutorial

nlp-tutorial is an educational repository that implements influential natural language processing models in concise PyTorch examples. Most implementations use fewer than 100 lines of executable code, making the architectures easier to inspect and modify. The curriculum begins with neural language models, Word2Vec, and FastText. It then covers TextCNN, recurrent networks, LSTM, bidirectional LSTM, sequence-to-sequence learning, and attention. Later examples implement the Transformer and BERT for translation, classification, and masked-token tasks. Paper links and Google Colab notebooks connect each implementation with its research background and an accessible runtime.