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

TL;DR

This paper presents a neural machine translation approach to generate natural language explanations for autonomous agents' actions, demonstrated in a game environment, improving human understanding and satisfaction.

Contribution

It introduces a novel rationalization technique using neural machine translation to produce human-like explanations of autonomous system behavior.

Findings

Neural machine translation accurately generates rationalizations.

Rationalizations are more satisfying to humans than other explanation methods.

The approach is effective in a game environment for explaining agent actions.

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.