# kamalkraj/BERT-NER

Pytorch-Named-Entity-Recognition-with-BERT

Repository: https://github.com/kamalkraj/BERT-NER
Canonical: https://ross.abutalabs.com/products/kamalkraj-bert-ner
Language: Python
License: AGPL-3.0
License Family: copyleft
Topics: bert, named-entity-recognition, pytorch, conll-2003, cpp11, bert-ner, inference, curl, postman, pretrained-models
Last push: 2021-05-06T19:38:36+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": 2747, "days_push": 1945, "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 1249, forks 272 (observed 2026-08-28T04:04:07.931159+00:00)

## What it is
A PyTorch library for training and running named entity recognition (NER) models based on Google's BERT, evaluated on the CoNLL-2003 dataset. It also provides a C++ inference path so trained models can be deployed without a Python runtime.

## Use cases
- extract names, locations, and organizations from text
- train a BERT model for named entity recognition on CoNLL-2003
- run NER inference in C++ for production deployment
- fine-tune pretrained BERT models on custom NER data
- tag tokens in a sentence with entity labels and confidence scores

## When to choose
- you need a simple, proven BERT-based NER pipeline in PyTorch
- you want fast C++ inference without Python dependencies
- you are working with the CoNLL-2003 entity extraction task

## When to avoid
- you need multi-language or multilingual NER out of the box
- you want a maintained library with recent updates and modern transformer support
- you need a full NLP toolkit rather than a focused NER implementation

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, nlp, llm-training
- domain: machine-learning, deep-learning
- platform: python, cpp
- tags: bert, named-entity-recognition, pytorch, conll-2003, ner, inference, transfer-learning, natural-language-processing, linux, macos

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

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:07.931159+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 2026-08-30T05:07:47.568996+00:00, confidence not recorded.
  - readme: https://github.com/kamalkraj/BERT-NER (fetched 2026-08-28T04:04:07.931159+00:00, sha b0e3cd825dfa)
- Data as of 2026-08-30T08:39:29.467469+00:00.