Language Processing Explained
From Words to Meaning, Before and After Large Language Models
- Pages
- 80
- Chapters
- 52
- Level
- Beginner–Intermediate
- Format
- E-book
About this book
Large language models dominate the conversation, but many language problems are solved better, cheaper or more transparently with other methods. This book gives you the whole toolkit.
It starts with how text is prepared and represented, then covers classic techniques (bag of words, TF-IDF, n-grams, naive Bayes), word embeddings, sequence models, and finally transformers and large language models. Task chapters address classification, extraction, search, summarisation and translation, with guidance on evaluation and multilingual challenges.
The aim is judgement: knowing which approach fits a problem.
What you will learn
- Preparing and representing text
- Classic methods: bag of words, TF-IDF and n-grams
- Word embeddings and what they capture
- From recurrent networks to transformers
- Classification, extraction, search and summarisation
- Choosing the right approach and evaluating it
Table of contents
- IntroductionIntroduction
- Chapter 1Why Language Is Hard for Computers
- Chapter 2Characters, Encodings and Unicode
- Chapter 3Tokenisation
- Chapter 4Normalisation
- Chapter 5Regular Expressions
- Chapter 6Bag of Words
- Chapter 7TF-IDF
- Chapter 8N-grams
- Chapter 9Measuring Text Similarity
- Chapter 10Naive Bayes for Text
- Chapter 11Logistic Regression for Text
- Chapter 12Classic Sequence Labelling
- Chapter 13Topic Models
- Chapter 14Words as Vectors
- Chapter 15Learning Word Embeddings
- Chapter 16Sentence and Document Embeddings
- Chapter 17Choosing Between Classic and Embedding Methods
- Chapter 18Recurrent Networks
- Chapter 19Encoder–Decoder Models
- Chapter 20Attention
- Chapter 21The Transformer
- Chapter 22Contextual Embeddings and Pre-training
- Chapter 23Large Language Models
- Chapter 24Prompting Versus Fine-Tuning
- Chapter 25Retrieval and Grounding
- Chapter 26Text Classification
- Chapter 27Sentiment Analysis
- Chapter 28Named Entity Recognition and Extraction
- Chapter 29Relation Extraction
- Chapter 30Search
- Chapter 31Summarisation
- Chapter 32Machine Translation
- Chapter 33Question Answering
- Chapter 34Text Generation
- Chapter 35Dialogue and Chatbots
- Chapter 36Text Simplification and Accessibility
- Chapter 37Speech and Text Together
- Chapter 38A Worked Classifier, From Raw Text to Prediction
- Chapter 39Building a Labelled Dataset for NLP
- Chapter 40Handling Long Documents
- Chapter 41Structured Output From Language Models
- Chapter 42Cost, Latency and Model Size
- Chapter 43Domain Adaptation
- Chapter 44Monitoring Language Over Time
- Chapter 45Evaluation
- Chapter 46Multilingual NLP
- Chapter 47Bias in Language Technology
- Chapter 48Privacy and Sensitive Text
- Chapter 49Choosing an Approach
- Chapter 50Case Study: Routing Support Tickets
- Chapter 51Case Study: Searching a Policy Library
- Chapter 52A Project Checklist
- AppendixExercises
- GlossaryGlossary
Who this book is for
Developers, analysts and students who want a complete, practical picture of language technology.
Details
| Format | PDF + web edition |
|---|---|
| Length | 80 pages (approx.) |
| Chapters | 52 |
| Level | Beginner to Intermediate |
| Language | English |
| Topic | Deep Learning |
| Author | Latent Library Editorial |
Keep reading