luopeixiang/named_entity_recognition resource

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

2285 stars · 527 forks observed · 2026-08-28

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

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

learning-resource · maturity maintenance

nlp machine-learning machine-learning education python named-entity-recognition sequence-labeling chinese-ner hmm crf bilstm bilstm-crf pytorch tutorial resume-ner natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="luopeixiang/named_entity_recognition")