Investigating Evaluation of Open-Domain Dialogue Systems With Human Generated Multiple References
This addresses evaluation challenges for researchers and developers in open-domain dialogue, but it is incremental as it builds on existing metrics and datasets.
The paper tackles the problem of poor correlation between automatic metrics and human judgment in evaluating open-domain dialogue systems by proposing multi-reference evaluation, showing that augmenting the DailyDialog test set with multiple references improves correlation for quality and diversity metrics.
The aim of this paper is to mitigate the shortcomings of automatic evaluation of open-domain dialog systems through multi-reference evaluation. Existing metrics have been shown to correlate poorly with human judgement, particularly in open-domain dialog. One alternative is to collect human annotations for evaluation, which can be expensive and time consuming. To demonstrate the effectiveness of multi-reference evaluation, we augment the test set of DailyDialog with multiple references. A series of experiments show that the use of multiple references results in improved correlation between several automatic metrics and human judgement for both the quality and the diversity of system output.