RUBER: An Unsupervised Method for Automatic Evaluation of Open-Domain Dialog Systems

TL;DR

RUBER is an unsupervised, learnable evaluation metric for open-domain dialog systems that correlates well with human judgment without needing labeled data.

Contribution

The paper introduces RUBER, a novel unsupervised evaluation method combining referenced and unreferenced metrics for dialog system assessment.

Findings

RUBER correlates highly with human judgments.

It is applicable to both retrieval and generative dialog systems.

The metric is flexible across datasets and languages.

Abstract

Open-domain human-computer conversation has been attracting increasing attention over the past few years. However, there does not exist a standard automatic evaluation metric for open-domain dialog systems; researchers usually resort to human annotation for model evaluation, which is time- and labor-intensive. In this paper, we propose RUBER, a Referenced metric and Unreferenced metric Blended Evaluation Routine, which evaluates a reply by taking into consideration both a groundtruth reply and a query (previous user-issued utterance). Our metric is learnable, but its training does not require labels of human satisfaction. Hence, RUBER is flexible and extensible to different datasets and languages. Experiments on both retrieval and generative dialog systems show that RUBER has a high correlation with human annotation.