III — Representations & Sequences

This part moves from sparse, count-based features to learned dense representations, and introduces models that process text as sequences.

Chapters in this part

• Chapter 3: Embeddings & Sequence Models — Word embeddings, neural sequence models (RNNs/LSTMs), and token-level classification.

What you'll be able to do

• Explain what word embeddings capture and how they are learned.
• Build recurrent models that consume and produce sequences.
• Perform token classification (e.g. tagging) with neural models.