interpretml/interpret-text

A library that incorporates state-of-the-art explainers for text-based machine learning models and visualizes the result with a built-in dashboard.

56
/ 100
Established

This tool helps data scientists and developers understand why their text-based AI models make specific predictions. You input your text classification or generative text model and sample data, and it outputs interactive visualizations that show how different words or phrases influence the model's decisions. This is designed for AI developers and data scientists who build and deploy machine learning models dealing with text.

432 stars. No commits in the last 6 months. Available on PyPI.

Use this if you need to debug, audit, or gain insights into the behavior of your text-based machine learning models, especially for understanding fairness or establishing governance.

Not ideal if you are not a developer or data scientist working with text-based machine learning models.

natural-language-processing ai-explainability text-classification model-auditing responsible-ai
Stale 6m
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 21 / 25

How are scores calculated?

Stars

432

Forks

68

Language

Python

License

MIT

Last pushed

Feb 05, 2024

Commits (30d)

0

Dependencies

14

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/interpretml/interpret-text"

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