Natural Language Processing
Embeddings, Transformers and Language Tasks
About this guide
A concise exam companion for natural language processing. It covers tokenisation and TF-IDF, classical text classification, word embeddings, n-gram and neural language models, recurrent networks, attention and transformers, contextual embeddings, and the core tasks from named entity recognition to translation and question answering, with evaluation, bias and safety. Every chapter ends with a worked example carried through step by step, so you can check the reasoning yourself.
Inside the guide
- TF-IDF
- Classical text classification
- Word embeddings
- N-gram and neural language models
- Recurrent networks
- Attention and transformers
- Contextual embeddings
- With evaluation
- Bias and safety
Questions students ask
What does Natural Language Processing cover?
It covers tokenisation and TF-IDF, classical text classification, word embeddings, n-gram and neural language models, recurrent networks, attention and transformers, contextual embeddings, and the core tasks from named entity recognition to translation and question answering, with evaluation, bias and safety.
Who is Natural Language Processing for?
It is written for university students revising natural language processing, and for lecturers and librarians choosing a clear, exam-focused reading-list text.
What format does it come in?
Kindle ebook and paperback on Amazon.
Can I read part of it for free?
Full Marks Press offers a free sample chapter at fullmarkspress.com/free, and the full guide is free to read with Kindle Unlimited.