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.
Supports multiple explanation techniques including unified information decomposition, introspective rationales, and likelihood-based methods—each with different trade-offs between model support (scikit-learn to PyTorch/HuggingFace/OpenAI) and preprocessing automation. Provides both global (label-level) and local (document-level) explanations with a unified API and Jupyter widget for interactive comparison across explainers. Built as an extension to the Interpret framework, enabling researchers to contribute custom interpretability techniques alongside established methods.
432 stars and 49 monthly downloads. No commits in the last 6 months. Available on PyPI.
Stars
432
Forks
68
Language
Python
License
MIT
Category
Last pushed
Feb 05, 2024
Monthly downloads
49
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...
jalammar/ecco
Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations...
fdalvi/NeuroX
A Python library that encapsulates various methods for neuron interpretation and analysis in...
alexdyysp/ESIM-pytorch
中国高校计算机大赛--大数据挑战赛
adaamko/POTATO
XAI based human-in-the-loop framework for automatic rule-learning.