csinva/interpretable-embeddings

Interpretable text embeddings by asking LLMs yes/no questions (NeurIPS 2024)

21
/ 100
Experimental

This tool helps you understand what complex text data is really about by converting it into a clear, yes/no profile. You input text examples and a list of specific yes/no questions relevant to your domain. The output is a simple table showing whether each question applies to each piece of text. Marketers, researchers, or anyone analyzing text content can use this to get actionable insights.

No commits in the last 6 months.

Use this if you need to quickly and transparently understand the key characteristics or themes present within a collection of text documents.

Not ideal if you need to generate numerical representations of text for machine learning models without a focus on human interpretability.

text-analysis content-categorization market-research qualitative-analysis document-tagging
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

46

Forks

2

Language

Python

License

Last pushed

Nov 15, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/csinva/interpretable-embeddings"

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