AlpacaTag: An Active Learning-based Crowd Annotation Framework for Sequence Tagging (ACL 2019 Demo)

A set of tools for leveraging pre-trained embeddings, active learning and model explainability for effecient document classification

Interactively create machine learning datasets using facets visualization tool and active learning or semi-supervised learning. Visualizations for machine learning datasets

Stratification of multi-label datasets

Codebase for study measuring the effect of different sequences of active/passive input for category learning.

A web-based graphical user interface to assist grading jupyter notebook assignments with required active learning query strategy and machine learning model.

Continuous Active Learning (CAL) for Predictive Coding: A Demonstration with Enron Spam-Ham Classification.

This repository is designed to document and explain in-detailed analysis of data, from concepts like mining or transforming to predictive analytics.