NoahFinberg/insight_extractor
A package of a simple version of the Considdr (2014-2020) ML model used to extract insights from full text documents.
This tool helps you quickly identify the most important, 'abstractive' sentences within a collection of text documents. You provide a list of sentences, and it gives you a probability score for each one, indicating how likely it is to be a key insight. Researchers, analysts, or anyone needing to distill core ideas from many texts would find this useful.
No commits in the last 6 months. Available on PyPI.
Use this if you need to quickly pinpoint the most significant statements in articles, reports, or research papers.
Not ideal if you need a full article summary or expect it to cluster related insights automatically; it focuses only on scoring individual sentences.
Stars
15
Forks
3
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Mar 21, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/NoahFinberg/insight_extractor"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
bcgov/tno
Today's News Online (TNO) is a news aggregation system that takes in news sources of varying...
marinaramalhete/nlp-toolkit
Multi-feature NLP toolkit built with Streamlit — text summarization, named entity recognition,...
baboonzero/invisible-threads
Discovers "invisible threads" - non-obvious insights that connect across 300+ podcast...
deepset-ai/haystack-search-pipeline-streamlit
🚀 Template Haystack Search Application with Streamlit
Mhackiori/STIXnet
A Novel and Modular Solution for Extracting All STIX Objects in CTI Reports