gianluigilopardo/anchors_text_theory

Code for the paper "A Sea of Words: An In-Depth Analysis of Anchors for Text Data", AISTATS 2023

19
/ 100
Experimental

This project helps machine learning researchers understand how "Anchors" work as a method for explaining text-based AI models. It takes in text data and trained AI models, then produces explanations and analyses of which parts of the text are most critical for a model's decisions. This is designed for researchers focused on the interpretability and explainability of natural language processing (NLP) models.

No commits in the last 6 months.

Use this if you are a machine learning researcher studying how text-based AI models make decisions and want to rigorously evaluate the 'Anchors' explainability technique.

Not ideal if you are an end-user simply looking to get explanations from your text AI models without deep theoretical analysis.

machine-learning-research NLP-explainability text-analytics AI-interpretability model-debugging
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 6 / 25

How are scores calculated?

Stars

14

Forks

1

Language

Python

License

Last pushed

Oct 26, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/gianluigilopardo/anchors_text_theory"

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