First part: NLP NLP Milestones One-Hot Encoding Languages NLP Glossary BPE - Byte Pair Encoding MED - Minimum Edit Distance N-Grams PPMI TF-IDF Viterbi Algorithm Second part: Word2Vec Loss Function Gradient Skipgram model with negative samples Chain rule and Jacobians Backpropagation Backpropagation for noobs RNN Vanishing Gradient Problem - LSTM NMT