AI Glossary Models and how they work

Natural language processing (NLP)

NLPnoun · pronounced "en-el-pee"

  • Tidio Agents team
  • Updated November 19, 2026
  • 5 min read
  • 5 sources
Definition

Natural language processing (NLP) is the field of computer science and AI that builds software to read, interpret, and produce human language, in text or speech. It covers tasks such as classifying a message's intent, extracting names and order numbers, detecting sentiment, translating, summarizing, and generating replies.

NLP is the parent field. Large language models are its most recent and most capable tool, but the field is decades older and the tasks it defined still structure how customer service software is built: work out what the customer wants, pull out the details, judge the mood, and respond.

What changed with LLMs is the method. Older systems needed a separate, hand-built component for each task. A modern model can do most of them from an instruction and a few examples.5

Origin

From rules to statistics to language models

NLP has gone through four broad approaches. Each one is still in use somewhere, often inside the same product.

1

Rules

Knowledge comes from: linguists and developers

Hand-written patterns and grammars. If the message contains "refund" and "order," route it to billing. Predictable and brittle: a synonym or a typo breaks it.

2

Statistical NLP

Knowledge comes from: labeled examples

N-gram language models and classifiers such as naive Bayes and logistic regression learn from counts in data instead of rules.1 Better coverage, but each task needs its own labeled dataset.

3

Neural embeddings

Knowledge comes from: large unlabeled text

Words become vectors that capture meaning, so "parcel" and "package" sit close together. Word2vec learned such vectors from 1.6 billion words in under a day.2

4

Pretrained transformers

Knowledge comes from: pretraining, then fine-tuning

The transformer architecture relies on attention alone.3 Models such as BERT are pretrained once and fine-tuned per task with one extra output layer.4

5

Large language modelsToday

Knowledge comes from: pretraining at scale, instructions

One model handles many tasks from a text instruction and a few examples, without retraining.5

Example

What NLP extracts from one message

A customer writes to an electronics retailer. Before any reply is drafted, NLP turns the free text into structured data the support system can act on.

Customer message
Mylaptoporder#48213arrivedwithacrackedscreen.Iwantareplacement,notarefund.Thirdtimethisyear.

Extracted: intent damaged item, replacement · entities product: laptop, order: 48213 · sentiment negative, repeat issue · constraint no refund

json
{
  "intent": "damaged_item.replacement",
  "entities": {"order_id": "48213", "product": "laptop", "damage": "cracked screen"},
  "sentiment": "negative",
  "signals": ["repeat_issue", "declines_refund"],
  "route": "returns_agent",
  "priority": "high"
}

Illustrative example of structured output. Field names are placeholders; each team defines its own schema.

Tasks

NLP tasks that matter in customer service

Intent recognition

Classifying what the customer wants: order status, return, cancellation, complaint. See intent recognition. It decides routing and which agent or workflow takes over.

Entity extraction

Pulling out order numbers, product names, dates, amounts, and addresses. See named entity recognition. Entities become the inputs to tool calls.

Sentiment analysis

Judging tone and frustration. See sentiment analysis. Used to prioritize, to adjust replies, and to hand angry customers to a person sooner.

Summarization

Condensing a long conversation into a handover note or a ticket summary, so a human agent does not have to reread the whole thread.

Generation

Writing the reply itself, in the brand's tone and the customer's language. Modern agents generate from retrieved policies rather than from templates.

Translation

Serving customers in several languages from one knowledge base, which matters for brands across Poland, CEE, Germany, and the UK.

Compared

NLP, NLU, LLMs, and conversational AI

These terms are often used as synonyms in vendor material. They sit at different levels.

TermWhat it namesRelationship to NLP
Natural language processingThe whole field of making software work with languageThe parent field
Natural language understanding (NLU)The interpretation side: intent, entities, meaningA subfield of NLP
Natural language generation (NLG)The production side: writing textA subfield of NLP
Large language modelA pretrained model that does many NLP tasks from instructions5Today's main NLP tool
Conversational AIProducts that hold a dialogue: chatbots, voice agentsAn application built with NLP
Machine learningLearning patterns from data, for any kind of dataThe broader method most modern NLP uses
In practice

Where NLP shows up in a support operation

Most of these run before or after the conversation, not only inside it.

Customer support

Triage every message

A telecom classifies incoming messages by intent and urgency, extracts the account number, and sends each to the right agent or queue.

message → intent + entities → route
Back office

Read documents

An insurer extracts claim numbers, dates, and amounts from emails and attachments and fills the claims system.

email → extract → post to system
Quality

Analyze every conversation

A marketplace tags all conversations by topic and sentiment to find what drives contacts, instead of reading a small sample.

transcripts → tag → report drivers
Shopping

Understand what shoppers mean

A retailer's shopping agent maps "something for a small balcony, under 300 złoty" to catalog filters for size and price.

need → entities → search catalog
Risks

Limits and the usual controls

Language and dialect gaps

ControlQuality varies by language. Test intent and entity accuracy in each language you serve, on real messages, before launch.

Misread intent

ControlAsk a clarifying question when confidence is low instead of guessing. Track misroutes as a metric.

Sarcasm and context

ControlSentiment models misjudge irony and short replies. Use sentiment to prioritize, not to make decisions on its own.

Personal data in text

ControlFree text contains names, addresses, and card numbers. Detect and mask personal data before storage or analysis.

FAQ

Common questions

Is NLP the same as AI?

No. NLP is one field within AI, focused on language. AI also covers vision, robotics, planning, and more.

Is ChatGPT NLP?

Yes. ChatGPT is built on a large language model, which is the current main technique in NLP. It performs NLP tasks such as understanding, summarizing, translating, and generating text.

What is the difference between NLP and NLU?

NLU, natural language understanding, is the part of NLP concerned with interpreting meaning, such as intent and entities. NLP also includes generating language, translation, and speech.

Do support teams still need separate NLP models if they use an LLM?

Sometimes. An LLM can classify intent and extract entities from instructions, but a small dedicated classifier or a rule can be cheaper, faster, and easier to audit for high-volume, stable tasks.

Sources

References

  1. Jurafsky, D. and Martin, J. H. Speech and Language Processing, 3rd edition draft. Stanford University, 2026.
  2. Mikolov, T. et al. Efficient Estimation of Word Representations in Vector Space. arXiv, 2013.
  3. Vaswani, A. et al. Attention Is All You Need. NeurIPS 2017.
  4. Devlin, J. et al. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL 2019.
  5. Brown, T. B. et al. Language Models are Few-Shot Learners. NeurIPS 2020.

Tidio Agents

Build an agent that resolves, not only answers

We design and build custom AI agents for customer service, shopping and back-office work, on your infrastructure, with the code handed over to you. Projects start with a 21-day private AI audit.

Request a call