AI glossary Conversational
What is natural language processing (NLP)?
NLP (Natural Language Processing)
← All glossary termsThe field of AI that enables computers to understand, analyse and generate human language, in text and speech.
Explained
Natural language processing (NLP) is the branch of AI concerned with human language. It covers understanding text and speech (what is being said, by whom, with what intent and tone) and producing it (answers, summaries, translations). The field moved from hand-written rules to statistical models and then to neural networks; today large language models handle many NLP tasks with a single model guided by instructions. NLP underpins chatbots and virtual assistants, search, document processing, translation and sentiment analysis.
Main NLP tasks
- Classification: assigning a label to text, such as topic, intent, urgency or sentiment.
- Information extraction: finding entities, fields and relations in documents.
- Search and question answering: finding the passage that answers a question.
- Summarisation: condensing long text into its key points.
- Translation: converting text between languages.
- Generation and dialogue: writing replies, drafts and conversations.
- Speech: recognising spoken language and synthesising voice, often treated alongside NLP.
From rules to large language models
Early NLP systems relied on grammars and rules written by experts. Statistical methods then learned patterns from labelled examples, one task at a time. Neural networks and, later, the transformer architecture led to models pre-trained on large amounts of text that could be adapted to many tasks.
Large language models took this further: with a prompt and a few examples, one model can classify, extract, summarise and translate. Specialised smaller models are still useful where cost, speed or privacy matter.
How businesses use it
- Routing and answering customer emails, chats and calls.
- Reading contracts, claims, invoices and forms.
- Searching internal knowledge in natural language.
- Analysing feedback, reviews and surveys at scale.
- Drafting reports, replies and documentation for people to review.
Frequently asked questions
What is NLP in simple terms?
It is the part of AI that lets computers work with human language: read it, understand it and write it. Every time software answers a question, sorts emails or translates a text, NLP is involved.
What is the difference between NLP and LLMs?
NLP is the field; large language models are one technology within it. LLMs are now the most capable general tool for NLP tasks, but NLP also includes older and smaller methods that are still used for specific jobs.
What are examples of NLP?
Spam filters, search engines, voice assistants, machine translation, chatbots, automatic summaries and tools that pull data from documents are all examples of NLP.
Is NLP the same as AI?
No. NLP is a subfield of AI, alongside others such as computer vision and robotics. It focuses on language, while AI as a whole covers any task that requires perception, reasoning or decision-making.
Is NLP still relevant with large language models?
Yes. The tasks and the evaluation methods of NLP remain the same; what changed is the main tool. Knowing NLP helps decide when an LLM is the right choice and when a smaller, cheaper model does the job.
How to put it to work
Where it shows up at Thinkia
Related terms
Sources
- Jurafsky and Martin · Speech and Language Processing (3rd ed. draft)
- Brown et al. · Language models are few-shot learners (arXiv)
- Devlin et al. · BERT: pre-training of deep bidirectional transformers for language understanding (arXiv)
Updated: 2026-10-21