# Determined22/zh-NER-TF

A very simple BiLSTM-CRF model for Chinese Named Entity Recognition 中文命名实体识别 (TensorFlow)

Repository: https://github.com/Determined22/zh-NER-TF
Canonical: https://ross.abutalabs.com/products/zh-ner-tf
Language: Python
License Family: other
Topics: named-entity-recognition, bilstm-crf-model, tensorflow
Last push: 2022-04-18T23:01:50+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3298, "days_push": 1598, "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 2333, forks 924 (observed 2026-08-28T04:06:37.871558+00:00)

## What it is
A simple character-based BiLSTM-CRF sequence labeling model for Chinese Named Entity Recognition built with TensorFlow 1.x. It recognizes PERSON, LOCATION, and ORGANIZATION entities and includes training/testing scripts plus preprocessed MSRA-style data files.

## Use cases
- recognize person, location, and organization names in Chinese text
- train a BiLSTM-CRF model for Chinese NER
- run sequence labeling on character-level Chinese corpora
- learn how CRF layers work on top of BiLSTM encoders
- train a custom NER model on my own tagged Chinese dataset

## When to choose
- you need a minimal, easy-to-read Chinese NER implementation for learning or prototyping
- you want a classic BiLSTM-CRF baseline for PERSON/LOC/ORG tagging in Chinese
- you have data in BIO character-level format and want a simple training pipeline

## When to avoid
- you need modern TensorFlow 2.x, PyTorch, or pretrained transformer-based NER models
- you need production-grade performance, maintenance, or a maintained license
- you need entity types beyond PER/LOC/ORG or multilingual support

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, nlp
- domain: machine-learning
- platform: python
- tags: named-entity-recognition, bilstm-crf, sequence-labeling, chinese-nlp, tensorflow, natural-language-processing

## Member repositories
- Determined22/zh-NER-TF (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:37.871558+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 2026-08-30T02:37:54.437315+00:00, confidence not recorded.
  - readme: https://github.com/Determined22/zh-NER-TF (fetched 2026-08-28T04:06:37.871558+00:00, sha 91e2a2f37022)
- Data as of 2026-08-30T08:39:29.467469+00:00.