A Study of Automatic Metrics for the Evaluation of Natural Language Explanations
This work addresses the need for reliable automatic evaluation methods in Explainable AI and transparent systems, though it is incremental as it applies existing NLG metrics to a new domain.
The study tackled the problem of evaluating automatically generated natural language explanations by investigating which NLG evaluation metrics best correlate with human ratings, finding that embedding-based methods like BERTScore and BLEURT had higher correlations than word-overlap metrics such as BLEU and ROUGE.
As transparency becomes key for robotics and AI, it will be necessary to evaluate the methods through which transparency is provided, including automatically generated natural language (NL) explanations. Here, we explore parallels between the generation of such explanations and the much-studied field of evaluation of Natural Language Generation (NLG). Specifically, we investigate which of the NLG evaluation measures map well to explanations. We present the ExBAN corpus: a crowd-sourced corpus of NL explanations for Bayesian Networks. We run correlations comparing human subjective ratings with NLG automatic measures. We find that embedding-based automatic NLG evaluation methods, such as BERTScore and BLEURT, have a higher correlation with human ratings, compared to word-overlap metrics, such as BLEU and ROUGE. This work has implications for Explainable AI and transparent robotic and autonomous systems.