doccano/spacy-partial-tagger

A simple library for training named entity recognition model from partially annotated data

38
/ 100
Emerging

This is a library for machine learning engineers and NLP developers to train named entity recognition (NER) models using partially labeled text data. It takes in a dataset where not all entities are annotated, often created using dictionary-based rules, and outputs a trained NER model that can identify entities in new text. This tool is for those who need to build accurate NER systems efficiently without fully hand-labeling every single entity.

No commits in the last 6 months. Available on PyPI.

Use this if you need to train a named entity recognition model from text data where only some entities are labeled, typically using a rule-based system or an existing dictionary.

Not ideal if you have a fully hand-annotated dataset for named entity recognition or if you are looking for a pre-trained, off-the-shelf NER model.

natural-language-processing machine-learning-engineering text-annotation information-extraction data-labeling
Stale 6m
Maintenance 0 / 25
Adoption 6 / 25
Maturity 25 / 25
Community 7 / 25

How are scores calculated?

Stars

24

Forks

2

Language

Jupyter Notebook

License

MIT

Last pushed

Nov 12, 2023

Commits (30d)

0

Dependencies

7

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/doccano/spacy-partial-tagger"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.