ACCENT: An Automatic Event Commonsense Evaluation Metric for Open-Domain Dialogue Systems
This addresses the problem of automated commonsense evaluation for dialogue systems, which is incremental as it focuses specifically on event commonsense.
The paper tackles the challenge of evaluating commonsense in open-domain dialogue systems by proposing ACCENT, a metric that uses commonsense knowledge bases to assess event relations, and shows it achieves higher correlations with human judgments than existing baselines.
Commonsense reasoning is omnipresent in human communications and thus is an important feature for open-domain dialogue systems. However, evaluating commonsense in dialogue systems is still an open challenge. We take the first step by focusing on event commonsense that considers events and their relations, and is crucial in both dialogues and general commonsense reasoning. We propose ACCENT, an event commonsense evaluation metric empowered by commonsense knowledge bases (CSKBs). ACCENT first extracts event-relation tuples from a dialogue, and then evaluates the response by scoring the tuples in terms of their compatibility with the CSKB. To evaluate ACCENT, we construct the first public event commonsense evaluation dataset for open-domain dialogues. Our experiments show that ACCENT is an efficient metric for event commonsense evaluation, which achieves higher correlations with human judgments than existing baselines.