:parrot: COCKATIEL (ACL 2023)

This repository contains code for the paper:

COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP, Fanny Jourdan*, Agustin Picard*, Thomas Fel, Laurent Risser, Jean Michel Loubes & Nicholas Asher. Findings of ACL 2023, [arXiv].

The code is implemented and available for Pytorch. A notebook is available: notebook example.

@article{jourdan2023cockatiel,
  title={COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP tasks},
  author={Jourdan, Fanny and Picard, Agustin and Fel, Thomas and Risser, Laurent and Loubes, Jean Michel and Asher, Nicholas},
  journal={arXiv preprint arXiv:2305.06754},
  year={2023}
}

Authors

• Fanny Jourdan - fanny.jourdan@irit.fr, PhD Student, ANITI/IRIT, Paul Sabatier University
• Agustin Picard - agustin-martin.picard@irt-saintexupery.com, Research engineer, IRT Saint Exupery