HUSTAI/uie_pytorch

PaddleNLP UIE模型的PyTorch版实现

49
/ 100
Emerging

Extracts specific information from Chinese or English text, such as names, dates, events, or relationships between entities. You provide the text and define what information you want to extract using natural language descriptions. This project outputs the identified pieces of information, their location in the text, and a confidence score. It's for data analysts, researchers, or anyone needing to quickly structure unstructured text from documents, reports, or reviews.

683 stars. No commits in the last 6 months.

Use this if you need to extract various types of information like entities, relationships, or sentiment from unstructured text without extensive manual labeling or model training.

Not ideal if you require specialized, highly accurate extraction for extremely niche or domain-specific data without any examples, or if you prefer using the PaddlePaddle deep learning framework.

information-extraction text-analysis data-structuring nlp-applications document-intelligence
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

683

Forks

120

Language

Python

License

Apache-2.0

Last pushed

Aug 13, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/HUSTAI/uie_pytorch"

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