Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.24721 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917528423366656 |
|---|---|
| author | Garland, Evelyn Y. Berger, Carola F. |
| author_facet | Garland, Evelyn Y. Berger, Carola F. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_24721 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ROC Analysis for Evaluating Translation Quality Estimation Systems Garland, Evelyn Y. Berger, Carola F. Computation and Language 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. |
| title | ROC Analysis for Evaluating Translation Quality Estimation Systems |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2605.24721 |