griff4692/calibrating-summaries

This is the official PyTorch codebase for the ACL 2023 paper: "What are the Desired Characteristics of Calibration Sets? Identifying Correlates on Long Form Scientific Summarization".

21
/ 100
Experimental

This toolkit helps scientific researchers and content creators improve the quality of automatically generated summaries for long-form scientific documents like chemistry papers or clinical studies. You provide the original scientific text and its summary, and the toolkit helps refine the summary to be more relevant or factually accurate. It's designed for anyone who relies on automated summarization for scientific content and needs to ensure high quality.

No commits in the last 6 months.

Use this if you need to rigorously evaluate and improve the relevance or faithfulness of machine-generated summaries for long scientific articles.

Not ideal if you are looking for a general-purpose summarization tool for non-scientific text or if you don't have existing summaries to calibrate against.

scientific-summarization academic-publishing research-analysis medical-research chemistry-research
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 8 / 25

How are scores calculated?

Stars

9

Forks

1

Language

Python

License

Last pushed

Aug 14, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/griff4692/calibrating-summaries"

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