View a PDF of the paper titled A Measure of the System Dependence of Automated Metrics, by Pius von D”aniken and 2 other authors
Abstract:Automated metrics for Machine Translation have made significant progress, with the goal of replacing expensive and time-consuming human evaluations. These metrics are typically assessed by their correlation with human judgments, which captures the monotonic relationship between human and metric scores. However, we argue that it is equally important to ensure that metrics treat all systems fairly and consistently. In this paper, we introduce a method to evaluate this aspect.
Submission history
From: Jan Deriu [view email]
[v1]
Wed, 4 Dec 2024 09:21:46 UTC (253 KB)
[v2]
Sat, 28 Dec 2024 17:21:27 UTC (253 KB)
Source link
lol