Contents
Course notes
Course home
Contents
Part I
Language as Data
1
What Natural Language Processing Is
2
Corpora and Preprocessing
3
The Empirical Laws of Text
4
Term Weighting and Similarity
5
Subword Tokenisation
Part II
Meaning as Geometry
6
Vector Space Models
7
Count Vectors, PPMI, and SVD
8
Neural Network Fundamentals
9
Learned Word Embeddings
Part III
Language Models
10
n-gram Language Models and Perplexity
11
Neural Language Models
12
Recurrent Networks
13
Gated Recurrence: LSTM and GRU
14
Text Classification and Evaluation
Part IV
The Transformer Era
15
Contextual Embeddings
16
Self-Attention and the Transformer
17
Pretrained Transformers: BERT and GPT
Part V
Working with Large Language Models
18
Steering LLMs: Decoding and Prompting
19
Adaptation and Alignment
20
Retrieval-Augmented Generation
21
Evaluating Generated Text
22
Building with Language Models
23
Efficiency: Smaller, Cheaper, Faster
Part VI
Applications
24
Machine Translation
25
Summarisation
Part VII
Responsible Practice
26
Responsible NLP
Projects and appendices
are handouts and reference code that live only in the PDF —
read them in the PDF edition
.
Next
What Natural Language Processing Is