Mediators: Conversational Agents Explaining NLP Model Behavior

2022/06/13 by Feldhus, Nils, Ravichandran, Ajay Madhavan, Möller, Sebastian
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2206.06029

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, text-based 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.

Related

• A Short Survey of Pre-trained Language Models for Conversational AI-A\n NewAge in NLP
• InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations
• Solving NLP Problems through Human-System Collaboration: A Discussion-based Approach
• Neural Conversation Models and How to Rein Them in: A Survey of Failures and Fixes
• Multi-Party Conversational Agents: A Survey