Rationalization: A Neural Machine Translation Approach to Generating Natural Language Explanations

Abstract

We introduce AI rationalization, an approach for generating explanations of autonomous system behavior as if a human had performed the behavior. We describe a rationalization technique that uses neural machine translation to translate internal state-action representations of an autonomous agent into natural language. We evaluate our technique in the Frogger game environment, training an autonomous game playing agent to rationalize its action choices using natural language. A natural language training corpus is collected from human players thinking out loud as they play the game. We motivate the use of rationalization as an approach to explanation generation and show the results of two experiments evaluating the effectiveness of rationalization. Results of these evaluations show that neural machine translation is able to accurately generate rationalizations that describe agent behavior, and that rationalizations are more satisfying to humans than other alternative methods of explanation.

arXiv comment9 pages, 4 figures; added human evaluation section; added author; changed author order-Upol Ehsan and Brent Harrison both contributed equally to this work

References in corpus (2)

• Understanding Neural Networks Through Deep Visualization
• Translating Neuralese

Cited by in corpus (9)

• The Pragmatic Turn in Explainable Artificial Intelligence (XAI)
• Contrastive Explanations with Local Foil Trees
• Explain Yourself: A Natural Language Interface for Scrutable Autonomous Robots
• Explainable PCGML via Game Design Patterns
• Using Program Induction to Interpret Transition System Dynamics
• Explaining Transition Systems through Program Induction
• Extractive Adversarial Networks: High-Recall Explanations for Identifying Personal Attacks in Social Media Posts
• Explanation of Reinforcement Learning Model in Dynamic Multi-Agent System
• Towards Automated Let's Play Commentary