ROC Analysis for Evaluating Translation Quality Estimation Systems
Computation and Language
2026-05-26 v1
Abstract
The increasing use of automated translation quality estimation (QE) systems calls for practical, decision-oriented methods for evaluating their performance. We propose that Receiver Operating Characteristic (ROC) analysis is a useful approach for this purpose. Our study shows that ROC analysis not only produces results consistent with currently prevalent methods, but also offers several important advantages, including actionable performance insights that support business decision-making.
Keywords
Cite
@article{arxiv.2605.24721,
title = {ROC Analysis for Evaluating Translation Quality Estimation Systems},
author = {Evelyn Y. Garland and Carola F. Berger},
journal= {arXiv preprint arXiv:2605.24721},
year = {2026}
}
Comments
16 pages, 8 PNG figures, 3 tables, uses acl.sty