# ahmetaa/zemberek-nlp

NLP tools for Turkish.

Repository: https://github.com/ahmetaa/zemberek-nlp
Canonical: https://ross.abutalabs.com/products/zemberek-nlp
Language: Java
License: NOASSERTION
License Family: other
Topics: morphology, language, nlp, zemberek-nlp, turkish
Last push: 2026-04-28T10:29:37+00:00

## Health v2 (maintenance only)
Score: 68/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 79, release rhythm 35, longevity 100
- inputs: {"age_days": 4839, "days_push": 127, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1352, forks 228 (observed 2026-08-28T04:04:28.501110+00:00)

## What it is
Zemberek-NLP is a Java library providing natural language processing tools for Turkish, including morphological analysis, tokenization, spell checking, named entity recognition, and text classification. It also ships console applications and a gRPC server for access from other languages.

## Use cases
- analyze Turkish word morphology
- spell check and suggest corrections for Turkish text
- tokenize Turkish sentences and detect sentence boundaries
- recognize named entities in Turkish text
- classify Turkish documents
- normalize noisy Turkish social media text
- identify the language of a text

## When to choose
- you need Turkish-specific NLP like morphology or disambiguation in a JVM project
- you want a mature, offline Turkish spell checker and word generator
- you need to expose Turkish NLP to non-JVM languages via gRPC

## When to avoid
- you need actively developed or state-of-the-art transformer-based Turkish NLP
- your project is not on the JVM and you cannot use the gRPC server
- you need NLP for languages other than Turkish

## Facets
- artifact type: library
- maturity: maintenance
- function: nlp, parser, search-engine
- domain: developer-tools
- platform: jvm, cross-platform
- tags: turkish, morphology, spell-checking, tokenization, named-entity-recognition, text-classification, grpc-server, natural-language-processing

## Member repositories
- ahmetaa/zemberek-nlp (main) score 68

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:28.501110+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 2026-08-30T04:42:08.144765+00:00, confidence not recorded.
  - readme: https://github.com/ahmetaa/zemberek-nlp (fetched 2026-08-28T04:04:28.501110+00:00, sha 374711f052bd)
- Data as of 2026-08-30T08:39:29.467469+00:00.