USR: An Unsupervised and Reference Free Evaluation Metric for Dialog Generation
Shikib Mehri, Maxine Eskénazi · 2020
The lack of meaningful automatic evaluation metrics for dialog has impeded open-domain dialog research.Standard language generation metrics have been shown to be ineffective for evaluating dialog models.To this end, this paper presents USR, an UnSupervised and Reference-free evaluation metric for dialog.USR is a reference-free metric that trains unsupervised models to measure several desirable qualities of dialog.USR is shown to strongly correlate with human judgment on both Topical-Chat (turn-level: 0.42, systemlevel: 1.0) and PersonaChat (turn-level: 0.48 and system-level: 1.0).USR additionally produces interpretable measures for several desirable properties of dialog.