Fritz449/ProtoNER

Few-shot classification in Named Entity Recognition Task

36
/ 100
Emerging

ProtoNER helps you identify specific entities, like names or locations, within text documents when you only have a few examples of what those entities look like. You provide a small set of labeled text examples, and the system learns to find similar entities in new, unlabeled text. This is useful for researchers or data scientists who need to extract structured information from domain-specific texts without extensive manual labeling.

No commits in the last 6 months.

Use this if you need to automatically extract specific types of information (named entities) from text, but you have very little pre-labeled data for your particular domain or entity types.

Not ideal if you already have large, well-labeled datasets for your named entity recognition task, or if you need a solution that doesn't require programming knowledge to implement.

text-analysis information-extraction natural-language-processing data-labeling machine-learning-research
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 19 / 25

How are scores calculated?

Stars

79

Forks

22

Language

Python

License

Last pushed

Dec 18, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/Fritz449/ProtoNER"

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