Contrastive Explanations of Text Classifiers as a Service

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


Abstract
The recent growth of black-box machine-learning methods in data analysis has increased the demand for explanation methods and tools to understand their behaviour and assist human-ML model cooperation. In this paper, we demonstrate ContrXT, a novel approach that uses natural language explanations to help users to comprehend how a back-box model works. ContrXT provides time contrastive (t-contrast) explanations by computing the differences in the classification logic of two different trained models and then reasoning on their symbolic representations through Binary Decision Diagrams. ContrXT is publicly available at ContrXT.ai as a python pip package.
Anthology ID:
2022.naacl-demo.6
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: System Demonstrations
Month:
July
Year:
2022
Address:
Hybrid: Seattle, Washington + Online
Editors:
Hannaneh Hajishirzi, Qiang Ning, Avi Sil
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
46–53
Language:
URL:
https://aclanthology.org/2022.naacl-demo.6
DOI:
10.18653/v1/2022.naacl-demo.6
Bibkey:
Cite (ACL):
Lorenzo Malandri, Fabio Mercorio, Mario Mezzanzanica, Navid Nobani, and Andrea Seveso. 2022. Contrastive Explanations of Text Classifiers as a Service. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: System Demonstrations, pages 46–53, Hybrid: Seattle, Washington + Online. Association for Computational Linguistics.
Cite (Informal):
Contrastive Explanations of Text Classifiers as a Service (Malandri et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-demo.6.pdf
Video:
 https://aclanthology.org/2022.naacl-demo.6.mp4