Natural Language Interaction with Explainable AI Models.

This paper presents an explainable AI (XAI) system that provides explanations for its predictions. The system consists of two key components -- namely, the prediction And-Or graph (AOG) model for recognizing and localizing concepts of interest in input data, and the XAI model for providing explanations to the user about the AOGu0027s predictions. In this work, we focus on the XAI model specified to interact with the user in natural language, whereas the AOGu0027s predictions are considered given and represented by the corresponding parse graphs (pgu0027s) of the AOG. Our XAI model takes pgu0027s as input and provides answers to the useru0027s questions using the following types of reasoning: direct evidence (e.g., detection scores), part-based inference (e.g., detected parts provide evidence for the concept asked), and other evidences from spatio-temporal context (e.g., constraints from the spatio-temporal surround). We identify several correlations between useru0027s questions and the XAI answers using Youtube Action dataset.