The quality of a summarization evaluation metric is quantified by calculating the correlation between its scores and human annotations across a large number of summaries. Currently, it is unclear how precise these correlation estimates are, nor whether differences between two metrics' correlations reflect a true difference or if it is due to mere chance. In this work, we address these two problems by proposing methods for calculating confidence intervals and running hypothesis tests for correlations using two resampling methods, bootstrapping and permutation. After evaluating which of the proposed methods is most appropriate for summarization through two simulation experiments, we analyze the results of applying these methods to several different automatic evaluation metrics across three sets of human annotations. We find that the confidence intervals are rather wide, demonstrating high uncertainty in the reliability of automatic metrics. Further, although many metrics fail to show statistical improvements over ROUGE, two recent works, QAEval and BERTScore, do in some evaluation settings.
翻译:总结性评价指标的质量是通过在大量摘要中计算其分数和人文说明的相互关系来量化的。目前,尚不清楚这些相关估计的准确性如何,或两个计量的相互关系之间的差异是否反映了真正的差异,或是否只是偶然的。在这项工作中,我们通过提出计算信任期的方法和采用两种重新采样方法对相互关系进行假设测试来解决这两个问题。在通过两个模拟实验对哪些拟议方法最适合进行总结之后,我们分析了将这些方法应用于三套人类说明的若干不同自动评价指标的结果。我们发现信任期相当宽,表明自动指标的可靠性有很大的不确定性。此外,虽然许多指标未能显示在ROUGE(两个近期的工程,QAEval和BERTScore)的统计方面有所改进,但在一些评价环境中,许多指标未能显示在两个最近的工程,即QAEval和BERTScore(QAval和BERTScore)方面的统计改进。