Resources

Textbook

The main reference is:

• Daniel Jurafsky and James H. Martin, Speech and Language Processing (3rd edition draft) — freely available online. Referred to as J&M on the lecture pages.

The official reading list is on Talis.

Reading map

Lecture	Reading
1. Introduction to text as data	J&M ch. 2
2. Bag-of-words, TF-IDF, cosine similarity	Lecture notes; Bholat et al. (2015)
3. Bag-of-words-based methods	Lecture notes; Baker, Bloom & Davis (2016)
4. N-gram language models	J&M ch. 2, 3, 7
5. Practical day 1	—
6. Word embeddings	J&M ch. 5, 6; Kozlowski et al. (2019)
7. LLMs and tokenization	J&M ch. 2, 7
8. Attention and transformers	J&M ch. 8; Jay Alammar’s illustrated guides
9. LLM training and fine-tuning	J&M ch. 8–10; Hugging Face NLP course ch. 1–3
10. Practical day 2	—
11. Prompt engineering and alignment	J&M ch. 7–9
12. Presentations	—

Supplementary material

• Andrej Karpathy, The spelled-out intro to language modeling: building makemore — hands-on companion to lectures 4 and 7.
• Jay Alammar, The Illustrated Transformer — visual companion to lecture 8.
• Hugging Face NLP course — chapters 1–3 accompany lectures 9 and 11.