ckiplab/ckiptagger

Health v2 · maintenance only

Adoption not part of the score

1684 stars · 188 forks observed · 2026-08-28

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

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

library · maturity stable

nlp machine-learning machine-learning python cross-platform chinese-nlp word-segmentation pos-tagging named-entity-recognition tensorflow traditional-chinese natural-language-processing

Member repositories

For agents

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