# kaiyinzhou/BERT-NER

Use Google's BERT for named entity recognition （CoNLL-2003 as the dataset）.

Repository: https://github.com/kaiyinzhou/BERT-NER
Canonical: https://ross.abutalabs.com/products/bert-ner
Language: Python
License: MIT
License Family: permissive
Topics: bert, ner, tensorflow, conll-2003, google-bert
Last push: 2022-05-19T05:06:32+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": 2856, "days_push": 1567, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1277, forks 325 (observed 2026-08-28T04:04:13.266816+00:00)

## What it is
A Python implementation that fine-tunes Google's BERT for named entity recognition using the CoNLL-2003 dataset, built on TensorFlow. It provides training, evaluation, and prediction scripts with optional CRF layer support for sequence labeling.

## Use cases
- train a named entity recognition model with BERT
- fine-tune BERT on CoNLL-2003 NER data
- recognize person, location, and organization names in text
- compare CRF vs softmax output layers for NER
- reproduce BERT NER benchmark results
- learn how to fine-tune BERT for sequence labeling

## When to choose
- you need a straightforward BERT-based NER implementation in TensorFlow
- you want a reference implementation for fine-tuning BERT on sequence labeling tasks
- you are working with the CoNLL-2003 dataset or a similar NER dataset

## When to avoid
- you need a maintained or production-ready NLP library
- you prefer PyTorch or modern transformer frameworks like Hugging Face
- you need multi-language or custom-domain NER out of the box
- you want the latest NLP model architectures beyond BERT

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, nlp, deep-learning
- domain: machine-learning, deep-learning
- platform: python, cross-platform
- tags: bert, named-entity-recognition, ner, tensorflow, conll-2003, fine-tuning, sequence-labeling, natural-language-processing, linux

## Member repositories
- kaiyinzhou/BERT-NER (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:13.266816+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 2026-08-30T05:02:50.607633+00:00, confidence not recorded.
  - readme: https://github.com/kaiyinzhou/BERT-NER (fetched 2026-08-28T04:04:13.266816+00:00, sha ae9c62933373)
- Data as of 2026-08-30T08:39:29.467469+00:00.