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.
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.
Stars
432
Forks
68
Language
Python
License
MIT
Category
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.
Related tools
rmovva/HypotheSAEs
HypotheSAEs: hypothesizing interpretable relationships in text datasets using sparse...
fdalvi/NeuroX
A Python library that encapsulates various methods for neuron interpretation and analysis in...
jalammar/ecco
Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations...
alexdyysp/ESIM-pytorch
中国高校计算机大赛--大数据挑战赛
MultiplEYE-COST/wg1-experiment-implementation
In this repository we keep the code for the implementation of the eye-tracking experiment for...