7. Midterm topics

7.1. Basic machine learning

  • Optimization: GD, SGD, convex functions

  • MLE

  • Overfitting and underfitting

  • F1 score

  • Train/dev/test split

7.2. Text representation

  • BoW representation

  • Feature templates

  • Word embeddings: skip-gram, CBOW

7.3. Language models

  • N-gram LM

  • Smoothing

  • Held-out likelihood, perplexity

7.4. Models

  • Logistic regression

  • Naive Bayes models

  • Conditional random fields

  • HMM (fully observered case)

  • Feed-forward neural nets

  • Recurrent neural nets

7.5. Inference

  • Viterbi decoding