AkihikoWatanabe / paper_notes

たまに追加される論文メモ
https://AkihikoWatanabe.github.io/paper_notes
21 stars 0 forks source link

Re-Examining System-Level Correlations of Automatic Summarization Evaluation Metrics, Deutsch+, NAACL'22 #952

Open AkihikoWatanabe opened 1 year ago

AkihikoWatanabe commented 1 year ago

https://aclanthology.org/2022.naacl-main.442/

AkihikoWatanabe commented 1 year ago

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.

Translation (by gpt-3.5-turbo)