# luopeixiang/named_entity_recognition

中文命名实体识别（包括多种模型：HMM，CRF，BiLSTM，BiLSTM+CRF的具体实现）

Repository: https://github.com/luopeixiang/named_entity_recognition
Canonical: https://ross.abutalabs.com/products/named_entity_recognition
Language: Python
License Family: other
Topics: named-entity-recognition, nlp, sequence-labeling, pytorch-nlp, hmm, crf, bi-lstm-crf, ner, bi-lstm, pytorch-ner, chinese-ner
Last push: 2022-06-21T21:48:08+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": 2722, "days_push": 1534, "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 2285, forks 527 (observed 2026-08-28T04:06:34.009603+00:00)

## What it is
A Chinese named entity recognition project implementing multiple sequence labeling models (HMM, CRF, BiLSTM, BiLSTM+CRF) in Python with PyTorch, trained and evaluated on the ResumeNER dataset from the LatticeLSTM paper. It serves primarily as an educational reference with detailed explanations of each model and includes an ensemble voting baseline.

## Use cases
- learn how to implement NER from scratch in Chinese
- compare HMM vs CRF vs BiLSTM vs BiLSTM+CRF on sequence labeling
- train a Chinese NER model on resume data
- understand BIOES tagging and Viterbi decoding
- study a reference implementation of CRF and HMM for NER
- get baseline F1 scores for Chinese NER models

## When to choose
- you want readable, well-commented implementations of classic NER models for learning
- you need a baseline comparison of HMM, CRF, BiLSTM, and BiLSTM+CRF on Chinese text
- you are studying sequence labeling with BIOES tags

## When to avoid
- you need production-grade NER with pretrained transformers like BERT
- you need a maintained library with an API rather than a research/teaching codebase
- you need a permissively licensed project (no license is specified)
- you need multilingual or English NER support

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: nlp, machine-learning
- domain: machine-learning, education
- platform: python
- tags: named-entity-recognition, sequence-labeling, chinese-ner, hmm, crf, bilstm, bilstm-crf, pytorch, tutorial, resume-ner, natural-language-processing

## Member repositories
- luopeixiang/named_entity_recognition (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:34.009603+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 2026-08-30T02:41:04.561104+00:00, confidence not recorded.
  - readme: https://github.com/luopeixiang/named_entity_recognition (fetched 2026-08-28T04:06:34.009603+00:00, sha ed70900f749d)
- Data as of 2026-08-30T08:39:29.467469+00:00.