Towards Explainable Linguistic Summaries

As more AI solutions are implemented in every aspect of our lives, the need for Explainable Artificial Intelligence (XAI) rises. Explanations can have different forms, such as a number (or an equation), a figure, or a text. This paper investigates textual explanations to effectively communicate the reason for a decision made by an AI system. In previous works, linguistic summaries, as an example of a textual explanation, have already been tested and shown to have explanatory potential. In this paper, we explore this topic further and present a roadmap for linguistic summaries to become a proper XAI tool as Explainable Linguistic Summaries (XLSs). We discuss the challenges that an XLS has to overcome. We outline possible solutions and state their consequences. We consider different protoforms, the definition of the membership function, heuristics for the selection of XLS and personalizing the explanations as well as options to gain more insights into the explanations.