Neural Networks for NLP

Chapter 11: Neural Basics for NLP Feed-forward networks, activation functions Backpropagation, optimization [Gradient descent, regularization, embedding layers] References Chapter 12: Recurrent and Convolutional Networks RNNs, LSTMs, GRUs; TextCNN, character-level CNNs Applications: Language modeling, sentiment analysis, text classification [Vanishing gradients, attention-augmented RNNs, 1D convolutions] References Chapter 13: Attention Mechanisms Attention in sequence models, additive vs. multiplicative attention Applications: Machine translation, sentiment analysis [Bahdanau attention, Luong attention, self-attention precursors] References