liveBook · Manning

Natural language processing

As explained in How Large Language Models Work

Natural language processing is the field concerned with technology for computers to understand, manipulate, and create human language.

Natural language processing (NLP) is the field where computer science and linguistics meet to develop technology that helps computers understand, manipulate, and create human language. Its history reaches back to 1940s efforts to automate translation. Modern language models belong to NLP, but their larger scale and much greater training data distinguish them from many earlier systems. section 1.1

NLP provides techniques used by large language models (LLMs), which are machine-learning models trained on large amounts of linguistic data. ChatGPT and similar tools use LLMs to accept and generate text, although fluent output does not by itself establish what the system understands. section 1.1

Figure 1.3 A high-level map of the various terms you’ll become familiar with and how they relate. Generative AI is a description of functionality: the function of generating content and using tech- niques from AI to accomplish that goal.
figure

Maps NLP, AI, generative AI, LLMs, and related tools in one high-level diagram. section 1.1

How How Large Language Models Work covers it

How deep it goes
Defines NLP and situates LLMs within it, but defers detailed transformer mechanics.
Examples
Uses automated translation, ChatGPT, Copilot, Claude, Gemini, text generation, and a generated haiku.
What you can do after
Evaluate/understand how NLP relates to generative AI, LLMs, and text-based chatbot products.
How it connects
Connects NLP with computer science, linguistics, artificial intelligence, machine learning, language models, and transformers.

Also explained in

Compare how 15 books explain natural language processing →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of How Large Language Models Work. The section links point to the parts of the book it draws on.