| Lesson | Topic | Details |
|---|---|---|
| 1 | Intro 1 | History of NLP, overview of course, class admin |
| 2 | Intro 2 | pandas, IO, spacy, POS, parses, stopwords |
| 3 | Representations | Discrete and sparse representations |
| 4 | Embeddings | Word2vec, doc2vec |
| 5 | Information retrieval 1 | TF-IDF, Entropy, and PMI |
| 6 | Information retrieval 2 | Collocations and RegEx |
| 7 | Language models 1 | probabilistic models, architecture, goals |
| 8 | Language models 2 | Trigram MLE model, smoothing |
| 9 | Topic models 1 | Model architecture, priors |
| 10 | Topic models 2 | Seeded topic models, preprocessing |
| 11 | Dimensionality reduction and Clustering | PCA/SVD, NMF, k-means, agglomerative clustering |
| 12 | Visualization | t-SNE, RGB mappings, seaborn |
| 13 | Midterm Project practice | |
| 14 | Retrofitting | |
| 15 | Text classification | Intro to classification, ethics |
| 16 | Improving classification performance and insights | metrics, significance, model and feature selection, regularization, RLR |
| 17 | Application: Sentiment Analysis | SA with LR and RLR |
| 18 | Neural networks basics | History, architecture, activation function, loss function, input-output differences |
| 19 | NN2 | Feed-forward Multilayer Perceptron in keras |
| 20 | NN3 | Convolutional neural networks for sequence problems |
| 21 | NN4 | Recurrent Neural Networks and attention |
| 22 | NN5 | RNNs in keras |
| 23 | Final Project Presentations | |
| 24 | Final Project Presentations |