natasha/natasha

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1347 stars · 120 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Natasha is a Python library that solves basic NLP tasks for the Russian language, including tokenization, sentence segmentation, morphology tagging, lemmatization, syntax parsing, NER, and fact extraction. It integrates lower-level Natasha project libraries (Razdel, Navec, Slovnet, Yargy, Ipymarkup) under one convenient API, with compact CPU-friendly models optimized for news articles.

Use cases

• extract named entities from Russian text
• tokenize and segment Russian sentences
• tag morphology and lemmatize Russian words
• parse syntax dependencies in Russian text
• extract facts like names and addresses from Russian documents
• visualize NER and syntax markups
• run Russian NLP models on CPU in production

When to choose

• you need production-ready Russian NLP with small, fast CPU models
• you want a single convenient API over multiple Russian NLP tools
• your text is news-like and you need NER, morphology, or syntax parsing

When to avoid

• you need NLP for languages other than Russian
• you need stable APIs for production — the README warns the API may change
• your domain text differs strongly from news articles, where model quality may drop

Facets

library · maturity active

nlp parser machine-learning data-visualization machine-learning python russian-language named-entity-recognition tokenization sentence-segmentation morphology syntax-parsing lemmatization embeddings fact-extraction natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="natasha/natasha")