# ckiplab/ckiptagger

CKIP Neural Chinese Word Segmentation, POS Tagging, and NER

Repository: https://github.com/ckiplab/ckiptagger
Canonical: https://ross.abutalabs.com/products/ckiptagger
Language: Python
License: GPL-3.0
License Family: copyleft
Last push: 2025-07-09T16:06:07+00:00

## Health v2 (maintenance only)
Score: 36/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 30, release rhythm 8, longevity 100
- inputs: {"age_days": 2567, "days_push": 420, "days_rel": 420, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1684, forks 188 (observed 2026-08-28T04:05:21.938113+00:00)

## What it is
CkipTagger is a Python library implementing neural CKIP-style Chinese NLP tools for word segmentation, part-of-speech tagging, and named entity recognition. It is built on TensorFlow/Keras and outperforms the classic CKIPWS and Jieba on Traditional Chinese benchmarks.

## Use cases
- segment Chinese text into words
- tag parts of speech in Chinese sentences
- extract named entities from Chinese text
- process Traditional Chinese NLP pipelines
- apply custom dictionaries for domain-specific segmentation
- handle very long Chinese sentences without truncation

## When to choose
- you need high-accuracy Traditional Chinese word segmentation, POS tagging, or NER
- you want a pip-installable neural alternative to Jieba or classic CKIPWS
- you need user-defined recommended-word or must-word lists
- you must process indefinitely long sentences

## When to avoid
- you need Simplified Chinese-focused tooling with a lighter dependency footprint
- you want a framework-agnostic library without TensorFlow/Keras
- GPL-3.0 licensing is incompatible with your project
- you need languages other than Chinese

## Facets
- artifact type: library
- maturity: stable
- function: nlp, machine-learning
- domain: machine-learning
- platform: python, cross-platform
- tags: chinese-nlp, word-segmentation, pos-tagging, named-entity-recognition, tensorflow, traditional-chinese, natural-language-processing

## Member repositories
- ckiplab/ckiptagger (main) score 36

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:21.938113+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 2026-08-30T03:41:16.452838+00:00, confidence not recorded.
  - readme: https://github.com/ckiplab/ckiptagger (fetched 2026-08-28T04:05:21.938113+00:00, sha 0358a446be73)
  - registry_pypi: https://pypi.org/pypi/ckiptagger/json (fetched 2026-08-29T11:13:56.952480+00:00, sha d58c3fc01bd5)
- Data as of 2026-08-30T08:39:29.467469+00:00.