Natural Language Interaction with Explainable AI Models

Arjun R Akula, Sinisa Todorovic, Joyce Y Chai, Song-Chun Zhu; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019, pp. 87-90


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 AOG's predictions. In this work, we focus on the XAI model specified to interact with the user in natural language, whereas the AOG's predictions are considered given and represented by the corresponding parse graphs (pg's) of the AOG. Our XAI model takes pg's as input and provides answers to the user's 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 spatiotemporal context (e.g., constraints from the spatiotemporal surround). We identify several correlations between user's questions and the XAI answers using Youtube Action dataset.

Related Material

author = {R Akula, Arjun and Todorovic, Sinisa and Y Chai, Joyce and Zhu, Song-Chun},
title = {Natural Language Interaction with Explainable AI Models},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2019}