# Język naturalny

EN: **Natural language processing** · id `nlp`

Path: [AI Atlas](https://aiatlasgraph.com/llms.txt) › [Język, obraz, audio](https://aiatlasgraph.com/t/modalities.md) › Język naturalny

## Description

- PL: Rozumienie i wytwarzanie języka.
- EN: Understanding and producing language.

## In one sentence

- PL: To dziedzina uczenia komputerów czytania, rozumienia i pisania tekstu w ludzkich językach.
- EN: This is the field of teaching computers to read, understand and write text in human languages.

## Problem it solves

- PL: Ludzie piszą i mówią swobodnie, a programy potrzebują uporządkowanych danych, więc ogromne ilości tekstu zostają nieprzeczytane.
- EN: People write and speak freely while software needs tidy data, so huge amounts of text go unread.

## What it does

- PL: Rozbija tekst na kawałki, uczy się, jak słowa zwykle występują razem, i na tej podstawie odpowiada, tłumaczy albo porządkuje.
- EN: It breaks text into pieces, learns how words usually go together, and uses that to answer, translate or sort.

## Everyday example

- PL: Skrzynka pocztowa sama odkłada reklamy do osobnego folderu, a telefon podpowiada następne słowo, gdy piszesz wiadomość.
- EN: Your inbox moves adverts into a separate folder on its own, and your phone suggests the next word as you type.

## This concerns you if you…

- PL: masz dużo tekstu do przeczytania lub uporządkowania
- PL: piszesz w języku innym niż angielski i chcesz dobrych wyników
- PL: chcesz rozmawiać z programem zwykłymi zdaniami
- EN: have more text than you can read or sort
- EN: work in languages with less training data
- EN: want to talk to software in ordinary sentences

## Keywords

BPE · contextual embeddings · BERT · sequence-to-sequence models · named entity recognition · natural language inference · SQuAD · ROUGE · BLEU · SentencePiece

## How it works

- PL: Tokeny i reprezentacje kontekstowe kodują formę oraz zależności w tekście. Reguły, modele statystyczne i sieci neuronowe przewidują etykiety, relacje lub kolejne fragmenty języka zgodnie z celem zadania.
- EN: Tokens and contextual representations encode textual form and dependencies. Rules, statistical models and neural networks predict labels, relations or subsequent language segments under task objectives.

## Limits

- PL: Wieloznaczność, kontekst i zmiany domeny utrudniają interpretację. Jakość zależy od języka i danych; poprawność gramatyczna nie gwarantuje zachowania znaczenia ani faktów.
- EN: Ambiguity, context and domain shifts complicate interpretation. Quality depends on language and data; grammatical correctness does not ensure preserved meaning or facts.

## Key terms

- PL: **token**: Jednostka tekstu przetwarzana przez model, niekoniecznie całe słowo.
- PL: **reprezentacja kontekstowa**: Wektor znaczenia elementu zależny od otaczającego tekstu.
- EN: **token**: A text unit processed by a model, not necessarily a whole word.
- EN: **contextual representation**: An element's vector representation depending on surrounding text.

## Know first

- [Uczenie nadzorowane (Supervised learning)](https://aiatlasgraph.com/t/supervised.md)
- [Teoria informacji: entropia i dywergencja KL (Information theory: entropy, cross-entropy and KL divergence)](https://aiatlasgraph.com/t/infotheory.md)

## Examples

- PL: Tłumaczenie · ekstrakcja · klasyfikacja
- EN: Translation · extraction · classification

## Subtopics (8 direct, 22 in total)

- [Automatyczna poprawa gramatyki i pisowni (Grammatical error correction)](https://aiatlasgraph.com/t/gec.md): Detecting and correcting grammatical, spelling and word-choice errors in text with minimal changes to content.
- [Klasyfikacja tekstu i analiza sentymentu (Text classification and sentiment analysis)](https://aiatlasgraph.com/t/textclassification.md): Assigning one or more labels to a text: sentiment, topic, spam, intent. Done today with a fine-tuned encoder or without task training — NLI-based zero-shot classification or prompting an LLM.
  - [Klasyfikacja tekstu bez przykładów (zero-shot) (Zero-shot text classification)](https://aiatlasgraph.com/t/zeroshotclassification.md): Assigning texts labels unseen in training, usually by recasting classes as NLI hypotheses or as an LLM prompt.
  - [Opinie o konkretnych cechach (sentyment aspektowy) (Aspect-based sentiment analysis)](https://aiatlasgraph.com/t/aspectsentiment.md): Extracting aspect-level opinions from text: aspect term, aspect category, opinion term and polarity.
  - [Wnioskowanie z tekstu: czy zdanie wynika z innego (NLI) (Natural language inference (textual entailment))](https://aiatlasgraph.com/t/nli.md): Classifying a premise–hypothesis pair as entailment, contradiction or neutral.
- [Odpowiadanie na pytania (QA) (Question answering (QA))](https://aiatlasgraph.com/t/questionanswering.md): Answering natural-language questions. Extractive QA selects an answer span from a supplied text; open-domain QA first retrieves relevant sources and then derives an answer. This retriever-reader pattern is closely related to later RAG systems.
  - [Odpowiadanie na pytania o dane w tabelach (Table question answering)](https://aiatlasgraph.com/t/tableqa.md): Answering natural-language questions from a table: selecting cells, aggregating, or generating a query such as SQL.
  - [Odpowiadanie na pytania z dużego zbioru tekstów (open-domain QA) (Open-domain question answering (retriever–reader))](https://aiatlasgraph.com/t/opendomainqa.md): Answering questions with no given context by retrieving passages from a large corpus and reading the answer from them.
  - [Wskazywanie odpowiedzi w podanym tekście (extractive QA) (Extractive question answering (reading comprehension))](https://aiatlasgraph.com/t/extractiveqa.md): Answering a question by selecting an answer span in a given context, or stating that the context has no answer.
- [Streszczanie tekstu (Text summarisation)](https://aiatlasgraph.com/t/summarization.md): Shortening a text while preserving its key information. Extractive summarisation selects source passages, while abstractive summarisation creates new wording; modern language models are widely used for abstractive summaries, where quality evaluation and faithfulness to the source remain important challenges.
  - [Streszczanie przez wybór najważniejszych zdań (Extractive summarisation)](https://aiatlasgraph.com/t/extractivesumm.md): Building a summary from selected source sentences or spans, without generating new text.
  - [Streszczanie własnymi słowami modelu (Abstractive summarisation)](https://aiatlasgraph.com/t/abstractivesumm.md): Generating a summary as new text with a sequence-to-sequence model or LLM, allowing paraphrase and information fusion.
- [Tokenizacja tekstu (BPE, WordPiece, SentencePiece) (Text tokenisation (BPE, WordPiece, SentencePiece))](https://aiatlasgraph.com/t/tokenization.md): Turning text into a sequence of tokens — sub-word pieces from a fixed vocabulary — before the model sees it. Sub-word methods dominate: BPE (also byte-level, as in GPT), WordPiece (BERT) and Unigram via SentencePiece (T5). Tokenisation affects cost, context length and how well a model handles non-English languages.
- [Tłumaczenie maszynowe (Machine translation)](https://aiatlasgraph.com/t/machinetranslation.md): Automatic translation of text between languages. It evolved from statistical systems to neural encoder–decoders with attention and Transformers, then to massively multilingual models and prompted LLMs.
  - [Ocena jakości tłumaczenia bez wzorca (quality estimation) (Machine translation quality estimation)](https://aiatlasgraph.com/t/mtqe.md): Predicting machine-translation quality from the source and translation alone, without a reference translation.
  - [Tłumaczenie mowy na inny język (Speech translation)](https://aiatlasgraph.com/t/speechtranslation.md): Translating source speech into target-language text or speech, either cascaded (ASR→MT→TTS) or directly with one model.
- [Wielojęzyczność i języki o małych zasobach (Multilingual and low-resource language processing)](https://aiatlasgraph.com/t/multilingualnlp.md): Processing many languages at once and languages with little data. It relies on cross-lingual transfer in shared multilingual models; quality for low-resource languages still lags clearly behind English.
- [Wydobywanie informacji z tekstu (nazwy własne, relacje) (Information extraction (named entities and relations))](https://aiatlasgraph.com/t/infoextraction.md): Turning free text into structured facts: named entities (NER — people, places, organisations, dates), relations and events. Classically done as token labelling; now also by LLMs emitting schema-constrained JSON or by compact zero-shot extractors.
  - [Rozpoznawanie nazw własnych (NER) (Named entity recognition (NER))](https://aiatlasgraph.com/t/ner.md): Labelling text spans with entity types such as person, organisation, location or date; classically framed as token classification with a BIO scheme.
  - [Rozwiązywanie koreferencji (kto to „on”?) (Coreference resolution)](https://aiatlasgraph.com/t/coreference.md): Clustering mentions (names, descriptions, pronouns) that refer to the same entity within a document.
  - [Wydobywanie relacji między encjami (Relation extraction)](https://aiatlasgraph.com/t/relationextraction.md): Identifying typed relations between entity pairs in text and recording them as (subject, relation, object) triples.
  - [Łączenie wzmianek z bazą wiedzy (entity linking) (Entity linking)](https://aiatlasgraph.com/t/entitylinking.md): Assigning a text mention the identifier of a knowledge-base entity, disambiguated by context.

## Sources

- [Hugging Face · Audio Course](<https://huggingface.co/learn/audio-course/en/chapter0/introduction>) `audio` · reference: Dane audio, klasyfikacja, ASR, TTS i modele mowy.
- [Stanford CS231n · Computer Vision (2026)](<https://cs231n.stanford.edu/>) `vision` · reference: Sieci neuronowe i rozumienie obrazów.
- [Stanford CS336 · Language Modeling from Scratch (2025)](<https://cs336.stanford.edu/spring2025/>) `cs336` · reference: Budowa modeli, dane, trening, systemy, inferencja i post-training.
- [DeepLearning.AI — course catalogue](<https://www.deeplearning.ai/courses>) `dlai` · course catalogue: 42 topic labels with counts, about 130 courses.
- [Hugging Face Tasks — natural language processing](<https://huggingface.co/tasks>) `hf-tasks-nlp` · by Hugging Face
- [Speech and Language Processing (3rd ed. draft) — table of contents](<https://web.stanford.edu/~jurafsky/slp3/>) `jurafsky-martin-slp3` · by Daniel Jurafsky, James H. Martin

---

AI Atlas revision 122 (2026-10-30) · HTML: https://aiatlasgraph.com/t/nlp · index: https://aiatlasgraph.com/llms.txt · everything: https://aiatlasgraph.com/llms-full.txt · updated 2026-10-30