OpenSUM/CPSUM

[COLING 2022] Code and Data Repo for Paper "Noise-injected Consistency Training and Entropy-constrained Pseudo Labeling for Semi-supervised Extractive Summarization"

21
/ 100
Experimental

This project helps researchers and data scientists working with large text corpuses to automatically create concise summaries. It takes long-form text documents, like news articles or reports, and outputs shorter summaries by extracting the most important sentences. This is useful for anyone who needs to quickly grasp the main points of many documents without reading them in full.

No commits in the last 6 months.

Use this if you need to generate summaries from a large collection of text documents and only have a small amount of human-labeled summary data available.

Not ideal if you need abstractive summaries (rewritten text) or have plenty of labeled data for supervised training.

text summarization natural language processing content analysis information extraction document analysis
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 5 / 25

How are scores calculated?

Stars

57

Forks

2

Language

Python

License

Last pushed

Mar 03, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/OpenSUM/CPSUM"

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