ownthink/Jiagu

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

3425 stars · 606 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Jiagu is a Python library for Chinese natural language processing built on deep learning models trained on large-scale corpora. It provides Chinese word segmentation, part-of-speech tagging, named entity recognition, sentiment analysis, knowledge graph relation extraction, keyword extraction, text summarization, new word discovery, and text clustering.

Use cases

• segment chinese text into words
• chinese part-of-speech tagging
• named entity recognition for chinese text
• extract relations for knowledge graphs from chinese text
• extract keywords from chinese documents
• summarize chinese articles
• sentiment analysis of chinese text
• discover new words from a corpus

When to choose

• you need an easy pip-installable toolkit for Chinese NLP tasks like segmentation, NER, and sentiment analysis
• you want relation extraction to bootstrap a Chinese knowledge graph from encyclopedic descriptions
• you need offline Chinese text mining utilities such as keyword extraction, summarization, or new word discovery

When to avoid

• you need production-grade NER or relation extraction with state-of-the-art accuracy and active support
• you primarily work with non-Chinese text
• you need long-term maintenance guarantees - the latest release dates to 2022

Facets

library · maturity maintenance

nlp machine-learning parser machine-learning large-language-models python cross-platform chinese-nlp word-segmentation named-entity-recognition part-of-speech-tagging sentiment-analysis relation-extraction knowledge-graph text-summarization keyword-extraction new-word-discovery text-clustering natural-language-processing

Member repositories

For agents

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