poteminr/instruct-ner

Instruct LLMs for flat and nested NER. Fine-tuning Llama and Mistral models for instruction named entity recognition. (Instruction NER)

37
/ 100
Emerging

This project helps domain experts extract specific terms from text, even when those terms are complex or overlap. You provide raw text and define the types of entities you want to find (like 'Drugname' or 'Drugform'). The system then uses large language models to identify and categorize these terms, giving you a structured list of extracted entities from your input text. It's designed for professionals who need to automatically tag and organize information within specialized texts.

No commits in the last 6 months.

Use this if you need to accurately identify and extract specific, predefined entities from text, especially in specialized fields like medicine, where you can customize what to look for.

Not ideal if your entity definitions are extremely broad, or if you need to extract entities that are deeply embedded and overlapping within complex text structures, as performance may be limited for very intricate nested entities.

information-extraction medical-informatics text-analysis data-tagging content-categorization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

89

Forks

9

Language

Python

License

Apache-2.0

Last pushed

May 05, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/poteminr/instruct-ner"

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