Congress 1279
Author/s
  • I. Stepin, A. Catala, Jose M. Alonso, M. Pereira
DOI
Source
  • Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence (NL4XAI) collocated with the 12th International Conference on Natural Language Generation (INLG). Tokyo, Japan. 2019

Paving the way towards counterfactual generation in argumentative conversational agents

Counterfactual explanations present an effective way to interpret predictions of black-box machine learning algorithms. Whereas thereis a significant body of research on counter-factual reasoning in philosophy and theoretical computer science, little attention has been paid to counterfactuals in regard to their explanatory capacity. In this paper, we review methods of argumentation theory and natural language generation that counterfactual explanation generation could benefit from most and discuss prospective directions for further re-search on counterfactual generation in explainable Artificial Intelligence.
Canonical link