The Good, the Bad, and the Explainer: A Tool for Contrastive Explanations of Text Classifiers

Lorenzo Malandri; Fabio Mercorio; Mario Mezzanzanica; Navid Nobani; Andrea Seveso

IJCAI 2022poster8 citations

The Good, the Bad, and the Explainer: A Tool for Contrastive Explanations of Text Classifiers

Lorenzo Malandri, Fabio Mercorio, Mario Mezzanzanica, Navid Nobani, Andrea Seveso

Abstract

In the last few years, we have been witnessing the increasing deployment of machine learning-based systems, which act as black boxes whose behaviour is hidden to end-users. As a side-effect, this contributes to increasing the need for explainable methods and tools to support the coordination between humans and ML models towards collaborative decision-making. In this paper, we demonstrate ContrXT, a novel tool that computes the differences in the classification logic of two distinct trained models, reasoning on their symbolic representation through Binary Decision Diagrams. ContrXT is available as a pip package and API.

Natural Language Processing: Interpretability and Analysis of Models for NLPAI Ethics, Trust, Fairness: Explainability and Interpretability

BibTeX

@inproceedings{ijcai2022p858,
  title     = {The Good, the Bad, and the Explainer: A Tool for Contrastive Explanations of Text Classifiers},
  author    = {Malandri, Lorenzo and Mercorio, Fabio and Mezzanzanica, Mario and Nobani, Navid and Seveso, Andrea},
  booktitle = {Proceedings of the Thirty-First International Joint Conference on
               Artificial Intelligence, {IJCAI-22}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Lud De Raedt},
  pages     = {5936--5939},
  year      = {2022},
  month     = {7},
  note      = {Demo Track},
  doi       = {10.24963/ijcai.2022/858},
  url       = {https://doi.org/10.24963/ijcai.2022/858},
}