Język naturalny

Natural language processing · id nlp

Rozumienie i wytwarzanie języka.

Understanding and producing language.

In one sentence

To dziedzina uczenia komputerów czytania, rozumienia i pisania tekstu w ludzkich językach.

This is the field of teaching computers to read, understand and write text in human languages.

Problem it solves

Ludzie piszą i mówią swobodnie, a programy potrzebują uporządkowanych danych, więc ogromne ilości tekstu zostają nieprzeczytane.

People write and speak freely while software needs tidy data, so huge amounts of text go unread.

What it does

Rozbija tekst na kawałki, uczy się, jak słowa zwykle występują razem, i na tej podstawie odpowiada, tłumaczy albo porządkuje.

It breaks text into pieces, learns how words usually go together, and uses that to answer, translate or sort.

Everyday example

Skrzynka pocztowa sama odkłada reklamy do osobnego folderu, a telefon podpowiada następne słowo, gdy piszesz wiadomość.

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…

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

Examples

• Tłumaczenie · ekstrakcja · klasyfikacja
• Translation · extraction · classification

Subtopics

• Automatyczna poprawa gramatyki i pisowni (Grammatical error correction): 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): 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): 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): 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)): Classifying a premise–hypothesis pair as entailment, contradiction or neutral.
• Odpowiadanie na pytania (QA) (Question answering (QA)): 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): 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)): 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)): Answering a question by selecting an answer span in a given context, or stating that the context has no answer.
• Streszczanie tekstu (Text summarisation): 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): Building a summary from selected source sentences or spans, without generating new text.
  • Streszczanie własnymi słowami modelu (Abstractive summarisation): 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)): 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): 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): Predicting machine-translation quality from the source and translation alone, without a reference translation.
  • Tłumaczenie mowy na inny język (Speech translation): 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): 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)): 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)): 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): Clustering mentions (names, descriptions, pronouns) that refer to the same entity within a document.
  • Wydobywanie relacji między encjami (Relation extraction): 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): Assigning a text mention the identifier of a knowledge-base entity, disambiguated by context.

Sources

• Hugging Face · Audio Course · reference: Dane audio, klasyfikacja, ASR, TTS i modele mowy.
• Stanford CS231n · Computer Vision (2026) · reference: Sieci neuronowe i rozumienie obrazów.
• Stanford CS336 · Language Modeling from Scratch (2025) · reference: Budowa modeli, dane, trening, systemy, inferencja i post-training.
• DeepLearning.AI — course catalogue · course catalogue: 42 topic labels with counts, about 130 courses.
• Hugging Face Tasks — natural language processing · Hugging Face
• Speech and Language Processing (3rd ed. draft) — table of contents · Daniel Jurafsky, James H. Martin