A Comprehensive Assessment of Dialog Evaluation Metrics

TL;DR

This paper systematically compares 23 dialog evaluation metrics across 10 datasets, analyzing their effectiveness at different levels and settings to guide future research in dialog system assessment.

Contribution

It provides the first comprehensive, multi-faceted comparison of recent dialog evaluation metrics, highlighting their strengths, weaknesses, and best practices for assessment.

Findings

Metrics vary significantly in performance across datasets.

Combining metrics can improve evaluation reliability.

Certain metrics perform better at dialog or turn level.

Abstract

Automatic evaluation metrics are a crucial component of dialog systems research. Standard language evaluation metrics are known to be ineffective for evaluating dialog. As such, recent research has proposed a number of novel, dialog-specific metrics that correlate better with human judgements. Due to the fast pace of research, many of these metrics have been assessed on different datasets and there has as yet been no time for a systematic comparison between them. To this end, this paper provides a comprehensive assessment of recently proposed dialog evaluation metrics on a number of datasets. In this paper, 23 different automatic evaluation metrics are evaluated on 10 different datasets. Furthermore, the metrics are assessed in different settings, to better qualify their respective strengths and weaknesses. Metrics are assessed (1) on both the turn level and the dialog level, (2) for different dialog lengths, (3) for different dialog qualities (e.g., coherence, engaging), (4) for different types of response generation models (i.e., generative, retrieval, simple models and state-of-the-art models), (5) taking into account the similarity of different metrics and (6) exploring combinations of different metrics. This comprehensive assessment offers several takeaways pertaining to dialog evaluation metrics in general. It also suggests how to best assess evaluation metrics and indicates promising directions for future work.