adaamko/POTATO
XAI based human-in-the-loop framework for automatic rule-learning.
This tool helps language experts and data scientists automatically discover and evaluate linguistic rules for classifying text, such as detecting offensive language or identifying relationships between entities in sentences. You provide text examples with their classifications (like 'positive' or 'negative'), and it outputs rules that explain these classifications using sentence structures. It's designed for someone working with natural language data who needs to understand why a text is categorized a certain way.
No commits in the last 6 months.
Use this if you need to extract clear, interpretable linguistic rules from text data to understand or predict categories, even with unlabeled examples.
Not ideal if you just need a black-box text classification model and don't require human-readable rules or explanations.
Stars
49
Forks
8
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jul 07, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/adaamko/POTATO"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
rmovva/HypotheSAEs
HypotheSAEs: hypothesizing interpretable relationships in text datasets using sparse...
interpretml/interpret-text
A library that incorporates state-of-the-art explainers for text-based machine learning models...
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