Franck-Dernoncourt/NeuroNER

Health v2 · maintenance only

Adoption not part of the score

1723 stars · 472 forks observed · 2026-08-28

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

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

application · maturity maintenance

nlp machine-learning deep-learning machine-learning deep-learning python cross-platform cli named-entity-recognition tensorflow spacy word-embeddings brat-annotation natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Franck-Dernoncourt/NeuroNER")