Core concepts
Natural Language Processing
The branch of AI focused on understanding, generating, and working with human language — covering everything from spell-check to ChatGPT.
01 ——
In plain English
Natural Language Processing (NLP) is the area of AI focused on language — both understanding what people write or say, and producing language back. It's the foundation behind chatbots, translation, sentiment analysis, summarisation, and voice assistants.
Classic NLP tasks:
- Sentiment analysis — is this review positive or negative?
- Named entity recognition — extract people, places, dates
- Translation — convert between languages
- Summarisation — condense long text
- Question answering — given a passage, answer a question about it
The LLM era: Before LLMs, each NLP task required its own specialised model. Today, a single LLM like GPT-4 or Claude can handle nearly all of them through prompting alone — which is why the term "NLP" is now often subsumed under "LLMs" in product marketing.
02 ——
Related terms
LLM
Large Language Model — the type of AI behind tools like ChatGPT and Claude, trained to understand and generate text.
AI
Artificial Intelligence — software that performs tasks normally requiring human intelligence, like understanding language, recognising images, or generating content.
Machine Learning
A type of AI where systems learn patterns from data rather than being explicitly programmed with rules.
Conversational AI
AI systems designed for natural back-and-forth dialogue with users — covering chatbots, voice assistants, and AI agents.
Semantic Search
Search that finds results by meaning rather than exact keyword matches — so "car" finds results about "automobile" too.
Back to glossaryLast reviewed May 2026