# buppt/ChineseNER

中文命名实体识别，实体抽取，tensorflow，pytorch，BiLSTM+CRF

Repository: https://github.com/buppt/ChineseNER
Canonical: https://ross.abutalabs.com/products/buppt-chinesener
Language: Python
License Family: other
Topics: ner, named-entity-recognition, chinese, bilstm-crf, tensorflow, pytorch
Last push: 2020-03-15T12:05:05+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2987, "days_push": 2362, "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 1463, forks 388 (observed 2026-08-28T04:04:47.796678+00:00)

## What it is
A simple Chinese named entity recognition (NER) implementation using BiLSTM+CRF in both TensorFlow and PyTorch. It includes training scripts and three open Chinese datasets (Boson, People's Daily 1998, MSRA) for entity extraction of names, locations, and organizations.

## Use cases
- train a Chinese NER model with BiLSTM+CRF
- extract entities like names, places, and organizations from Chinese text
- learn how sequence labeling and CRF work with a minimal example
- run named entity recognition on a text file and write results to another file
- experiment with pretrained word embeddings for Chinese NER

## When to choose
- you want a minimal, easy-to-read BiLSTM+CRF NER implementation for Chinese
- you need a learning resource or baseline for Chinese entity extraction
- you want bundled open Chinese NER datasets to start training immediately

## When to avoid
- you need production-grade accuracy or actively maintained code (last updated 2020, old TensorFlow 1.7/PyTorch 0.4, Python 2.7)
- you need multilingual NER or transformer-based models
- you need fast training - the PyTorch version has no batching and is very slow

## Facets
- artifact type: library
- maturity: maintenance
- function: nlp, machine-learning, deep-learning
- domain: machine-learning, localization
- platform: python, windows
- tags: named-entity-recognition, bilstm-crf, chinese-ner, tensorflow, pytorch, entity-extraction, natural-language-processing, linux, macos

## Member repositories
- buppt/ChineseNER (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:47.796678+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 2026-08-30T04:35:12.016943+00:00, confidence not recorded.
  - readme: https://github.com/buppt/ChineseNER (fetched 2026-08-28T04:04:47.796678+00:00, sha e71458b16c9d)
- Data as of 2026-08-30T08:39:29.467469+00:00.