Re-Examining System-Level Correlations of Automatic Summarization Evaluation Metrics
This work addresses a critical issue for researchers and practitioners in NLP by highlighting the need for better human judgments and improved metrics, but it is incremental as it refines existing evaluation methods.
The paper tackles the problem of unreliable system-level correlations in automatic summarization evaluation metrics by proposing two changes to their calculation, demonstrating that ROUGE's correlation to human judgments is near zero in realistic scenarios.
How reliably an automatic summarization evaluation metric replicates human judgments of summary quality is quantified by system-level correlations. We identify two ways in which the definition of the system-level correlation is inconsistent with how metrics are used to evaluate systems in practice and propose changes to rectify this disconnect. First, we calculate the system score for an automatic metric using the full test set instead of the subset of summaries judged by humans, which is currently standard practice. We demonstrate how this small change leads to more precise estimates of system-level correlations. Second, we propose to calculate correlations only on pairs of systems that are separated by small differences in automatic scores which are commonly observed in practice. This allows us to demonstrate that our best estimate of the correlation of ROUGE to human judgments is near 0 in realistic scenarios. The results from the analyses point to the need to collect more high-quality human judgments and to improve automatic metrics when differences in system scores are small.