Chapter 11: Natural Language Processing
Chapter Overview
Text-to-features pipeline · Embeddings · Tokenization · NLP tasks · Generation · Translation · RAG
Sections
1
Text Pipeline: From Raw Text to Features
Preprocessing · BoW · TF-IDF
2
Embeddings & Tokenization
3
The NLP Task Landscape
Classification · NER · QA · Summarization
4
Text Generation and Translation
Decoding · MT · BLEU · Multilingual
5
Retrieval-Augmented Generation
Dense retrieval · Chunking · Reranking
6
Nice to Know
Tooling · Metrics · Augmentation