Ties Matter: Meta-Evaluating Modern Metrics with Pairwise Accuracy and Tie Calibration
Submission Type: Regular Long Paper
Submission Track: Machine Translation
Submission Track 2: Resources and Evaluation
Keywords: meta-evaluation, metrics, kendall's tau
TL;DR: This work demonstrates the flaws of Kendall's tau with respect to ties for meta-evaluating evaluation metrics and proposes a pairwise accuracy statistic that fixes Kendall's shortcomings.
Abstract: Kendall's tau is frequently used to meta-evaluate how well machine translation (MT) evaluation metrics score individual translations. Its focus on pairwise score comparisons is intuitive but raises the question of how ties should be handled, a gray area that has motivated different variants in the literature. We demonstrate that, in settings like modern MT meta-evaluation, existing variants have weaknesses arising from their handling of ties, and in some situations can even be gamed. We propose instead to meta-evaluate metrics with a version of pairwise accuracy that gives metrics credit for correctly predicting ties, in combination with a tie calibration procedure that automatically introduces ties into metric scores, enabling fair comparison between metrics that do and do not predict ties. We argue and provide experimental evidence that these modifications lead to fairer ranking-based assessments of metric performance.
Submission Number: 4728
Loading