davidberenstein1957/concise-concepts

This repository contains an easy and intuitive approach to few-shot NER using most similar expansion over spaCy embeddings. Now with entity scoring.

37
/ 100
Emerging

This project helps you quickly identify specific terms or 'concepts' in text, even if they aren't explicitly listed. You provide a few examples for each concept, and it processes your text to find all relevant mentions, categorizing them with a score. This is useful for anyone working with unstructured text who needs to automatically extract key information, like a data analyst or researcher.

244 stars. No commits in the last 6 months.

Use this if you need to quickly find mentions of specific concepts in text without manually listing every possible variation, using just a few examples.

Not ideal if you need to train a very robust, comprehensive Named Entity Recognition model from scratch with extensive labeled datasets.

text-analysis information-extraction data-labeling content-categorization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

244

Forks

14

Language

Python

License

MIT

Last pushed

Jun 19, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/davidberenstein1957/concise-concepts"

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