# Franck-Dernoncourt/NeuroNER

Named-entity recognition using neural networks. Easy-to-use and state-of-the-art results.

Repository: https://github.com/Franck-Dernoncourt/NeuroNER
Canonical: https://ross.abutalabs.com/products/neuroner
Homepage: http://neuroner.com
Language: Python
License: MIT
License Family: permissive
Topics: nlp, machine-learning, neural-networks, named-entity-recognition, deep-learning, tensorflow
Last push: 2023-03-24T22:29:09+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3467, "days_push": 1258, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1723, forks 472 (observed 2026-08-28T04:05:27.869294+00:00)

## What it is
NeuroNER is a Python/TensorFlow program that performs named-entity recognition (NER) using neural networks, with pretrained models and an easy-to-use CLI and Python API. It optionally integrates with the BRAT annotation tool for creating annotations and viewing predictions.

## Use cases
- extract named entities from text with neural networks
- train a custom NER model on my own annotated dataset
- use a pretrained NER model for CoNLL-2003 style entity recognition
- de-identify medical texts with i2b2 2014 NER
- annotate text and view NER predictions in BRAT
- run named-entity recognition from the command line

## When to choose
- you need an easy-to-use, ready-to-run NER system with pretrained models
- you want to train NER models on custom datasets with TensorFlow 1.x
- you want BRAT integration for annotation workflows

## When to avoid
- you need modern TensorFlow 2.x or PyTorch support
- you need actively developed state-of-the-art transformer-based NER
- you require Python 2 compatibility

## Facets
- artifact type: application
- maturity: maintenance
- function: nlp, machine-learning, deep-learning
- domain: machine-learning, deep-learning
- platform: python, cross-platform, cli
- tags: named-entity-recognition, tensorflow, spacy, word-embeddings, brat-annotation, natural-language-processing

## Member repositories
- Franck-Dernoncourt/NeuroNER (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:27.869294+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 2026-08-30T03:33:56.098946+00:00, confidence not recorded.
  - readme: https://github.com/Franck-Dernoncourt/NeuroNER (fetched 2026-08-28T04:05:27.869294+00:00, sha 324355091a87)
  - homepage: http://neuroner.com (fetched 2026-08-29T11:09:22.318417+00:00, sha db3240cfb4e5)
- Data as of 2026-08-30T08:39:29.467469+00:00.