Publication
Mediators: Conversational Agents Explaining NLP Model Behavior
Nils Feldhus; Ajay Madhavan Ravichandran; Sebastian Möller
In: Rosina Weber; Ofra Amir; Tim Miller (Hrsg.). IJCAI 2022 - Workshop on Explainable Artificial Intelligence (XAI). IJCAI Workshop on Explainable Artificial Intelligence (XAI-2022), located at IJCAI-ECAI 2022, July 23, Vienna, Austria, International Joint Conferences on Artificial Intelligence Organization, 7/2022.
Abstract
The human-centric explainable artificial intelligence (HCXAI) community has raised the need for framing the explanation process as a conversation between human and machine. In this position paper, we establish desiderata for Mediators, textbased conversational agents which are capable of explaining the behavior of neural models interactively using natural language. From the perspective of natural language processing (NLP) research, we engineer a blueprint of such a Mediator for the task of sentiment analysis and assess how far along current research is on the path towards dialogue-based explanations.