# natasha/natasha

Solves basic Russian NLP tasks, API for lower level Natasha projects

Repository: https://github.com/natasha/natasha
Canonical: https://ross.abutalabs.com/products/natasha-natasha
Language: Python
License: MIT
License Family: permissive
Topics: nlp, russian, tokenizer, sentence-segmentation, embeddings, morphology, syntax, ner, visualization, python
Last push: 2026-04-13T19:39:01+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 77, release rhythm 35, longevity 100
- inputs: {"age_days": 3682, "days_push": 142, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1347, forks 120 (observed 2026-08-28T04:04:27.639796+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: nlp, parser, machine-learning, data-visualization
- domain: machine-learning
- platform: python
- tags: russian-language, named-entity-recognition, tokenization, sentence-segmentation, morphology, syntax-parsing, lemmatization, embeddings, fact-extraction, natural-language-processing

## Member repositories
- natasha/natasha (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:27.639796+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:42:37.730583+00:00, confidence not recorded.
  - readme: https://github.com/natasha/natasha (fetched 2026-08-28T04:04:27.639796+00:00, sha 91ff012bf14e)
  - registry_pypi: https://pypi.org/pypi/natasha/json (fetched 2026-08-29T12:01:35.373815+00:00, sha 372c54804a00)
- Data as of 2026-08-30T08:39:29.467469+00:00.