Lecture notes

• 1. Overview
  • 1.1. A brief history
  • 1.2. Challenges in NLP
  • 1.3. Course overview
  • 1.4. Additional readings
• 2. Basic machine learning
  • 2.1. Modeling, learning, inference
  • 2.2. Loss functions and optimization
  • 2.3. Summary
• 3. Text classification
  • 3.1. An intuitive approach
  • 3.2. Naive Bayes model
  • 3.3. Maximum likelihood estimation
  • 3.4. Logistic regression
  • 3.5. Bag-of-words (BoW) representation
  • 3.6. Feature extractor
  • 3.7. Evaluation
  • 3.8. Additional readings
• 4. Distributed word representations
  • 4.1. Vector-space models
  • 4.2. Learning word embeddings
  • 4.3. Brown clusters
  • 4.4. Evaluation
  • 4.5. Additional readings
• 5. Language models
  • 5.1. N-gram language models
  • 5.2. Neural language models
  • 5.3. Evaluation
  • 5.4. Additional reading
• 6. Sequence labeling
  • 6.1. A multiclass classification approach
  • 6.2. Structrured prediction
  • 6.3. Neural sequence labeling
  • 6.4. Applications
  • 6.5. Additional reading
• 7. Midterm topics
  • 7.1. Basic machine learning
  • 7.2. Text representation
  • 7.3. Language models
  • 7.4. Models
  • 7.5. Inference