# CLUEbenchmark/CLUENER2020

CLUENER2020 中文细粒度命名实体识别 Fine Grained Named Entity Recognition

Repository: https://github.com/CLUEbenchmark/CLUENER2020
Canonical: https://ross.abutalabs.com/products/cluener2020
Homepage: https://arxiv.org/abs/2001.04351
Language: Python
License Family: other
Topics: ner, chinese, bert, chinese-ner, fine-grained-ner, roberta, named-entity-recognition, sequence-labeling, albert, seq2seq, sequence-to-sequence, dataset, chinesener
Last push: 2022-11-21T08:05:14+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": 2432, "days_push": 1381, "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 1521, forks 296 (observed 2026-08-28T04:04:57.900817+00:00)

## What it is
CLUENER2020 is a fine-grained Chinese named entity recognition dataset and benchmark with 10 entity categories (address, book, company, game, government, movie, name, organization, position, scene), containing ~10,748 training and 1,343 validation sentences. It also provides baseline models such as BERT, RoBERTa, and BiLSTM+CRF for sequence labeling evaluation.

## Use cases
- train a Chinese named entity recognition model
- benchmark NER models on Chinese text
- fine-tune BERT for Chinese sequence labeling
- evaluate fine-grained entity extraction in Chinese
- get labeled Chinese NER training data
- compare Chinese NER model performance against baselines

## When to choose
- you need a well-defined, challenging Chinese NER dataset with diverse entity categories beyond person/location/organization
- you want to benchmark Chinese NER models against published baselines and a leaderboard

## When to avoid
- you need NER data for languages other than Chinese
- you need a permissively licensed dataset - the repo has no license specified
- you need actively maintained tooling rather than a dataset and baselines

## Facets
- artifact type: dataset
- maturity: maintenance
- function: nlp, machine-learning, benchmarking
- domain: machine-learning, artificial-intelligence
- platform: python
- tags: named-entity-recognition, chinese-ner, sequence-labeling, bert, fine-grained-ner, benchmark, seq2seq, natural-language-processing

## Member repositories
- CLUEbenchmark/CLUENER2020 (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:57.900817+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 2026-08-30T04:31:49.829824+00:00, confidence not recorded.
  - readme: https://github.com/CLUEbenchmark/CLUENER2020 (fetched 2026-08-28T04:04:57.900817+00:00, sha ac8cd0e8bf56)
  - homepage: https://arxiv.org/abs/2001.04351 (fetched 2026-08-29T11:34:52.598523+00:00, sha 67fd9d0012c2)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T11:34:52.607918+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T11:34:52.612072+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T11:34:52.613999+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T11:34:52.609880+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.